420 files changed, 7627 insertions, 5627 deletions

diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index a73a8e208a4a..96e54bed5088 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -1,7 +1,9 @@
 
-generic-y += clkdev.h
 
+generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += exec.h
-generic-y += trace_clock.h
-generic-y += preempt.h
 generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/alpha/include/asm/cputime.h b/arch/alpha/include/asm/cputime.h
deleted file mode 100644
index 19577fd93230..000000000000
--- a/arch/alpha/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ALPHA_CPUTIME_H
-#define __ALPHA_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __ALPHA_CPUTIME_H */
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 0d3362991c31..e76fd79f32b0 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,15 +1,15 @@
 generic-y += auxvec.h
 generic-y += barrier.h
-generic-y += bugs.h
 generic-y += bitsperlong.h
+generic-y += bugs.h
 generic-y += clkdev.h
 generic-y += cputime.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += errno.h
-generic-y += fcntl.h
 generic-y += fb.h
+generic-y += fcntl.h
 generic-y += ftrace.h
 generic-y += hardirq.h
 generic-y += hash.h
@@ -22,6 +22,7 @@ generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += param.h
@@ -30,6 +31,7 @@ generic-y += pci.h
 generic-y += percpu.h
 generic-y += poll.h
 generic-y += posix_types.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sembuf.h
@@ -48,4 +50,3 @@ generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
-generic-y += preempt.h
diff --git a/arch/arc/mm/cache_arc700.c b/arch/arc/mm/cache_arc700.c
index 6b58c1de7577..400c663b21c2 100644
--- a/arch/arc/mm/cache_arc700.c
+++ b/arch/arc/mm/cache_arc700.c
@@ -282,7 +282,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
 #else
         /* if V-P const for loop, PTAG can be written once outside loop */
         if (full_page_op)
-                write_aux_reg(ARC_REG_DC_PTAG, paddr);
+                write_aux_reg(aux_tag, paddr);
 #endif
 
         while (num_lines-- > 0) {
@@ -296,7 +296,7 @@ static inline void __cache_line_loop(unsigned long paddr, unsigned long vaddr,
                 write_aux_reg(aux_cmd, vaddr);
                 vaddr += L1_CACHE_BYTES;
 #else
-                write_aux_reg(aux, paddr);
+                write_aux_reg(aux_cmd, paddr);
                 paddr += L1_CACHE_BYTES;
 #endif
         }
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e25419817791..15949459611f 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1578,6 +1578,7 @@ config BL_SWITCHER_DUMMY_IF
 
 choice
         prompt "Memory split"
+        depends on MMU
         default VMSPLIT_3G
         help
           Select the desired split between kernel and user memory.
@@ -1595,6 +1596,7 @@ endchoice
 
 config PAGE_OFFSET
         hex
+        default PHYS_OFFSET if !MMU
         default 0x40000000 if VMSPLIT_1G
         default 0x80000000 if VMSPLIT_2G
         default 0xC0000000
@@ -1903,6 +1905,7 @@ config XEN
         depends on ARM && AEABI && OF
         depends on CPU_V7 && !CPU_V6
         depends on !GENERIC_ATOMIC64
+        depends on MMU
         select ARM_PSCI
         select SWIOTLB_XEN
         select ARCH_DMA_ADDR_T_64BIT
diff --git a/arch/arm/boot/compressed/.gitignore b/arch/arm/boot/compressed/.gitignore
index 47279aa96a6a..0714e0334e33 100644
--- a/arch/arm/boot/compressed/.gitignore
+++ b/arch/arm/boot/compressed/.gitignore
@@ -1,4 +1,5 @@
 ashldi3.S
+bswapsdi2.S
 font.c
 lib1funcs.S
 hyp-stub.S
diff --git a/arch/arm/boot/dts/bcm11351.dtsi b/arch/arm/boot/dts/bcm11351.dtsi
index e491b82f8d67..792fde1b7f75 100644
--- a/arch/arm/boot/dts/bcm11351.dtsi
+++ b/arch/arm/boot/dts/bcm11351.dtsi
@@ -147,7 +147,7 @@
         };
 
         pinctrl@35004800 {
-                compatible = "brcm,capri-pinctrl";
+                compatible = "brcm,bcm11351-pinctrl";
                 reg = <0x35004800 0x430>;
         };
 
diff --git a/arch/arm/boot/dts/keystone-clocks.dtsi b/arch/arm/boot/dts/keystone-clocks.dtsi
index 2363593e1050..ef58d1c24313 100644
--- a/arch/arm/boot/dts/keystone-clocks.dtsi
+++ b/arch/arm/boot/dts/keystone-clocks.dtsi
@@ -612,7 +612,7 @@ clocks {
                 compatible = "ti,keystone,psc-clock";
                 clocks = <&chipclk13>;
                 clock-output-names = "vcp-3";
-                reg = <0x0235000a8 0xb00>, <0x02350060 0x400>;
+                reg = <0x023500a8 0xb00>, <0x02350060 0x400>;
                 reg-names = "control", "domain";
                 domain-id = <24>;
         };
diff --git a/arch/arm/boot/dts/omap3-gta04.dts b/arch/arm/boot/dts/omap3-gta04.dts
index c551e4af4d83..d3b253bbc885 100644
--- a/arch/arm/boot/dts/omap3-gta04.dts
+++ b/arch/arm/boot/dts/omap3-gta04.dts
@@ -13,7 +13,7 @@
 
 / {
         model = "OMAP3 GTA04";
-        compatible = "ti,omap3-gta04", "ti,omap3";
+        compatible = "ti,omap3-gta04", "ti,omap36xx", "ti,omap3";
 
         cpus {
                 cpu@0 {
diff --git a/arch/arm/boot/dts/omap3-igep0020.dts b/arch/arm/boot/dts/omap3-igep0020.dts
index 25a2b5f652fd..f2779ac75872 100644
--- a/arch/arm/boot/dts/omap3-igep0020.dts
+++ b/arch/arm/boot/dts/omap3-igep0020.dts
@@ -14,7 +14,7 @@
 
 / {
         model = "IGEPv2 (TI OMAP AM/DM37x)";
-        compatible = "isee,omap3-igep0020", "ti,omap3";
+        compatible = "isee,omap3-igep0020", "ti,omap36xx", "ti,omap3";
 
         leds {
                 pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/omap3-igep0030.dts b/arch/arm/boot/dts/omap3-igep0030.dts
index 145c58cfc8ac..2793749eb1ba 100644
--- a/arch/arm/boot/dts/omap3-igep0030.dts
+++ b/arch/arm/boot/dts/omap3-igep0030.dts
@@ -13,7 +13,7 @@
 
 / {
         model = "IGEP COM MODULE (TI OMAP AM/DM37x)";
-        compatible = "isee,omap3-igep0030", "ti,omap3";
+        compatible = "isee,omap3-igep0030", "ti,omap36xx", "ti,omap3";
 
         leds {
                 pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/sama5d36.dtsi b/arch/arm/boot/dts/sama5d36.dtsi
index 6c31c26e6cc0..db58cad6acd3 100644
--- a/arch/arm/boot/dts/sama5d36.dtsi
+++ b/arch/arm/boot/dts/sama5d36.dtsi
@@ -8,8 +8,8 @@
  */
 #include "sama5d3.dtsi"
 #include "sama5d3_can.dtsi"
-#include "sama5d3_emac.dtsi"
 #include "sama5d3_gmac.dtsi"
+#include "sama5d3_emac.dtsi"
 #include "sama5d3_lcd.dtsi"
 #include "sama5d3_mci2.dtsi"
 #include "sama5d3_tcb1.dtsi"
diff --git a/arch/arm/boot/dts/sun4i-a10.dtsi b/arch/arm/boot/dts/sun4i-a10.dtsi
index 10666ca8aee1..249b6e0ba737 100644
--- a/arch/arm/boot/dts/sun4i-a10.dtsi
+++ b/arch/arm/boot/dts/sun4i-a10.dtsi
@@ -331,7 +331,7 @@
                 };
 
                 intc: interrupt-controller@01c20400 {
-                        compatible = "allwinner,sun4i-ic";
+                        compatible = "allwinner,sun4i-a10-ic";
                         reg = <0x01c20400 0x400>;
                         interrupt-controller;
                         #interrupt-cells = <1>;
@@ -403,7 +403,7 @@
                 };
 
                 timer@01c20c00 {
-                        compatible = "allwinner,sun4i-timer";
+                        compatible = "allwinner,sun4i-a10-timer";
                         reg = <0x01c20c00 0x90>;
                         interrupts = <22>;
                         clocks = <&osc24M>;
@@ -426,7 +426,7 @@
                 };
 
                 rtp: rtp@01c25000 {
-                        compatible = "allwinner,sun4i-ts";
+                        compatible = "allwinner,sun4i-a10-ts";
                         reg = <0x01c25000 0x100>;
                         interrupts = <29>;
                 };
diff --git a/arch/arm/boot/dts/sun5i-a10s.dtsi b/arch/arm/boot/dts/sun5i-a10s.dtsi
index 64961595e8d6..ddb25452d78e 100644
--- a/arch/arm/boot/dts/sun5i-a10s.dtsi
+++ b/arch/arm/boot/dts/sun5i-a10s.dtsi
@@ -294,7 +294,7 @@
                 };
 
                 intc: interrupt-controller@01c20400 {
-                        compatible = "allwinner,sun4i-ic";
+                        compatible = "allwinner,sun4i-a10-ic";
                         reg = <0x01c20400 0x400>;
                         interrupt-controller;
                         #interrupt-cells = <1>;
@@ -366,7 +366,7 @@
                 };
 
                 timer@01c20c00 {
-                        compatible = "allwinner,sun4i-timer";
+                        compatible = "allwinner,sun4i-a10-timer";
                         reg = <0x01c20c00 0x90>;
                         interrupts = <22>;
                         clocks = <&osc24M>;
@@ -383,7 +383,7 @@
                 };
 
                 rtp: rtp@01c25000 {
-                        compatible = "allwinner,sun4i-ts";
+                        compatible = "allwinner,sun4i-a10-ts";
                         reg = <0x01c25000 0x100>;
                         interrupts = <29>;
                 };
diff --git a/arch/arm/boot/dts/sun5i-a13.dtsi b/arch/arm/boot/dts/sun5i-a13.dtsi
index 320335abfccd..b373c74a9b3d 100644
--- a/arch/arm/boot/dts/sun5i-a13.dtsi
+++ b/arch/arm/boot/dts/sun5i-a13.dtsi
@@ -275,7 +275,7 @@
                 ranges;
 
                 intc: interrupt-controller@01c20400 {
-                        compatible = "allwinner,sun4i-ic";
+                        compatible = "allwinner,sun4i-a10-ic";
                         reg = <0x01c20400 0x400>;
                         interrupt-controller;
                         #interrupt-cells = <1>;
@@ -329,7 +329,7 @@
                 };
 
                 timer@01c20c00 {
-                        compatible = "allwinner,sun4i-timer";
+                        compatible = "allwinner,sun4i-a10-timer";
                         reg = <0x01c20c00 0x90>;
                         interrupts = <22>;
                         clocks = <&osc24M>;
@@ -346,7 +346,7 @@
                 };
 
                 rtp: rtp@01c25000 {
-                        compatible = "allwinner,sun4i-ts";
+                        compatible = "allwinner,sun4i-a10-ts";
                         reg = <0x01c25000 0x100>;
                         interrupts = <29>;
                 };
diff --git a/arch/arm/boot/dts/sun6i-a31.dtsi b/arch/arm/boot/dts/sun6i-a31.dtsi
index 5256ad9be52c..38d43febda4c 100644
--- a/arch/arm/boot/dts/sun6i-a31.dtsi
+++ b/arch/arm/boot/dts/sun6i-a31.dtsi
@@ -190,6 +190,14 @@
                 #size-cells = <1>;
                 ranges;
 
+                nmi_intc: interrupt-controller@01f00c0c {
+                        compatible = "allwinner,sun6i-a31-sc-nmi";
+                        interrupt-controller;
+                        #interrupt-cells = <2>;
+                        reg = <0x01f00c0c 0x38>;
+                        interrupts = <0 32 4>;
+                };
+
                 pio: pinctrl@01c20800 {
                         compatible = "allwinner,sun6i-a31-pinctrl";
                         reg = <0x01c20800 0x400>;
@@ -231,7 +239,7 @@
                 };
 
                 timer@01c20c00 {
-                        compatible = "allwinner,sun4i-timer";
+                        compatible = "allwinner,sun4i-a10-timer";
                         reg = <0x01c20c00 0xa0>;
                         interrupts = <0 18 4>,
                                      <0 19 4>,
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 9ff09484847b..cadcf2f9881d 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -339,6 +339,14 @@
                 #size-cells = <1>;
                 ranges;
 
+                nmi_intc: interrupt-controller@01c00030 {
+                        compatible = "allwinner,sun7i-a20-sc-nmi";
+                        interrupt-controller;
+                        #interrupt-cells = <2>;
+                        reg = <0x01c00030 0x0c>;
+                        interrupts = <0 0 4>;
+                };
+
                 emac: ethernet@01c0b000 {
                         compatible = "allwinner,sun4i-a10-emac";
                         reg = <0x01c0b000 0x1000>;
@@ -435,7 +443,7 @@
                 };
 
                 timer@01c20c00 {
-                        compatible = "allwinner,sun4i-timer";
+                        compatible = "allwinner,sun4i-a10-timer";
                         reg = <0x01c20c00 0x90>;
                         interrupts = <0 22 4>,
                                      <0 23 4>,
@@ -454,7 +462,7 @@
                 rtc: rtc@01c20d00 {
                         compatible = "allwinner,sun7i-a20-rtc";
                         reg = <0x01c20d00 0x20>;
-                        interrupts = <0 24 1>;
+                        interrupts = <0 24 4>;
                 };
 
                 sid: eeprom@01c23800 {
@@ -463,7 +471,7 @@
                 };
 
                 rtp: rtp@01c25000 {
-                        compatible = "allwinner,sun4i-ts";
+                        compatible = "allwinner,sun4i-a10-ts";
                         reg = <0x01c25000 0x100>;
                         interrupts = <0 29 4>;
                 };
@@ -596,10 +604,10 @@
                 hstimer@01c60000 {
                         compatible = "allwinner,sun7i-a20-hstimer";
                         reg = <0x01c60000 0x1000>;
-                        interrupts = <0 81 1>,
-                                     <0 82 1>,
-                                     <0 83 1>,
-                                     <0 84 1>;
+                        interrupts = <0 81 4>,
+                                     <0 82 4>,
+                                     <0 83 4>,
+                                     <0 84 4>;
                         clocks = <&ahb_gates 28>;
                 };
 
diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi
index 8b67b19392ec..789d0bacc110 100644
--- a/arch/arm/boot/dts/zynq-7000.dtsi
+++ b/arch/arm/boot/dts/zynq-7000.dtsi
@@ -24,6 +24,12 @@
                         device_type = "cpu";
                         reg = <0>;
                         clocks = <&clkc 3>;
+                        operating-points = <
+                                /* kHz    uV */
+                                666667  1000000
+                                333334  1000000
+                                222223  1000000
+                        >;
                 };
 
                 cpu@1 {
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 00fe9e9710fd..27d69b558c5d 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -204,7 +204,10 @@ CONFIG_MMC_BLOCK_MINORS=16
 CONFIG_MMC_SDHCI=y
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_SDHCI_TEGRA=y
+CONFIG_NEW_LEDS=y
+CONFIG_LEDS_CLASS=y
 CONFIG_LEDS_GPIO=y
+CONFIG_LEDS_TRIGGERS=y
 CONFIG_LEDS_TRIGGER_TIMER=y
 CONFIG_LEDS_TRIGGER_ONESHOT=y
 CONFIG_LEDS_TRIGGER_HEARTBEAT=y
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 3278afe2c3ab..23e728ecf8ab 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -7,16 +7,19 @@ generic-y += current.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += hash.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += local.h
 generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += msgbuf.h
 generic-y += param.h
 generic-y += parport.h
 generic-y += poll.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += sections.h
 generic-y += segment.h
@@ -33,5 +36,3 @@ generic-y += termios.h
 generic-y += timex.h
 generic-y += trace_clock.h
 generic-y += unaligned.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 8756e4bcdba0..4afb376d9c7c 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -30,14 +30,15 @@
  */
 #define UL(x) _AC(x, UL)
 
+/* PAGE_OFFSET - the virtual address of the start of the kernel image */
+#define PAGE_OFFSET             UL(CONFIG_PAGE_OFFSET)
+
 #ifdef CONFIG_MMU
 
 /*
- * PAGE_OFFSET - the virtual address of the start of the kernel image
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
  */
-#define PAGE_OFFSET             UL(CONFIG_PAGE_OFFSET)
 #define TASK_SIZE               (UL(CONFIG_PAGE_OFFSET) - UL(SZ_16M))
 #define TASK_UNMAPPED_BASE      ALIGN(TASK_SIZE / 3, SZ_16M)
 
@@ -104,10 +105,6 @@
 #define END_MEM                 (UL(CONFIG_DRAM_BASE) + CONFIG_DRAM_SIZE)
 #endif
 
-#ifndef PAGE_OFFSET
-#define PAGE_OFFSET             PLAT_PHYS_OFFSET
-#endif
-
 /*
  * The module can be at any place in ram in nommu mode.
  */
diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h
index 58b8b84adcd2..2fe85fff5cca 100644
--- a/arch/arm/include/asm/topology.h
+++ b/arch/arm/include/asm/topology.h
@@ -20,9 +20,6 @@ extern struct cputopo_arm cpu_topology[NR_CPUS];
 #define topology_core_cpumask(cpu)      (&cpu_topology[cpu].core_sibling)
 #define topology_thread_cpumask(cpu)    (&cpu_topology[cpu].thread_sibling)
 
-#define mc_capable()    (cpu_topology[0].socket_id != -1)
-#define smt_capable()   (cpu_topology[0].thread_id != -1)
-
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 47cd974e57ea..c96ecacb2021 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -177,6 +177,18 @@ __lookup_processor_type_data:
         .long   __proc_info_end
         .size   __lookup_processor_type_data, . - __lookup_processor_type_data
 
+__error_lpae:
+#ifdef CONFIG_DEBUG_LL
+        adr     r0, str_lpae
+        bl      printascii
+        b       __error
+str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n"
+#else
+        b       __error
+#endif
+        .align
+ENDPROC(__error_lpae)
+
 __error_p:
 #ifdef CONFIG_DEBUG_LL
         adr     r0, str_p1
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 914616e0bdcd..f5f381d91556 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -102,7 +102,7 @@ ENTRY(stext)
         and     r3, r3, #0xf                    @ extract VMSA support
         cmp     r3, #5                          @ long-descriptor translation table format?
  THUMB( it      lo )                            @ force fixup-able long branch encoding
-        blo     __error_p                       @ only classic page table format
+        blo     __error_lpae                    @ only classic page table format
 #endif
 
 #ifndef CONFIG_XIP_KERNEL
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 92f7b15dd221..adabeababeb0 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -30,7 +30,6 @@
 #include <linux/uaccess.h>
 #include <linux/random.h>
 #include <linux/hw_breakpoint.h>
-#include <linux/cpuidle.h>
 #include <linux/leds.h>
 #include <linux/reboot.h>
 
@@ -133,7 +132,11 @@ EXPORT_SYMBOL_GPL(arm_pm_restart);
 
 void (*arm_pm_idle)(void);
 
-static void default_idle(void)
+/*
+ * Called from the core idle loop.
+ */
+
+void arch_cpu_idle(void)
 {
         if (arm_pm_idle)
                 arm_pm_idle();
@@ -168,15 +171,6 @@ void arch_cpu_idle_dead(void)
 #endif
 
 /*
- * Called from the core idle loop.
- */
-void arch_cpu_idle(void)
-{
-        if (cpuidle_idle_call())
-                default_idle();
-}
-
-/*
  * Called by kexec, immediately prior to machine_kexec().
  *
  * This must completely disable all secondary CPUs; simply causing those CPUs
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 1d8248ea5669..bd18bb8b2770 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -878,7 +878,8 @@ static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
                                     unsigned long cmd,
                                     void *v)
 {
-        if (cmd == CPU_PM_EXIT) {
+        if (cmd == CPU_PM_EXIT &&
+            __hyp_get_vectors() == hyp_default_vectors) {
                 cpu_init_hyp_mode(NULL);
                 return NOTIFY_OK;
         }
diff --git a/arch/arm/kvm/interrupts.S b/arch/arm/kvm/interrupts.S
index ddc15539bad2..0d68d4073068 100644
--- a/arch/arm/kvm/interrupts.S
+++ b/arch/arm/kvm/interrupts.S
@@ -220,6 +220,10 @@ after_vfp_restore:
  * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
  * passed in r0 and r1.
  *
+ * A function pointer with a value of 0xffffffff has a special meaning,
+ * and is used to implement __hyp_get_vectors in the same way as in
+ * arch/arm/kernel/hyp_stub.S.
+ *
  * The calling convention follows the standard AAPCS:
  *   r0 - r3: caller save
  *   r12:     caller save
@@ -363,6 +367,11 @@ hyp_hvc:
 host_switch_to_hyp:
         pop     {r0, r1, r2}
 
+        /* Check for __hyp_get_vectors */
+        cmp     r0, #-1
+        mrceq   p15, 4, r0, c12, c0, 0  @ get HVBAR
+        beq     1f
+
         push    {lr}
         mrs     lr, SPSR
         push    {lr}
@@ -378,7 +387,7 @@ THUMB(	orr	lr, #1)
         pop     {lr}
         msr     SPSR_csxf, lr
         pop     {lr}
-        eret
+1:      eret
 
 guest_trap:
         load_vcpu                       @ Load VCPU pointer to r0
diff --git a/arch/arm/mach-davinci/da850.c b/arch/arm/mach-davinci/da850.c
index 2ab00434b2eb..85399c98f84a 100644
--- a/arch/arm/mach-davinci/da850.c
+++ b/arch/arm/mach-davinci/da850.c
@@ -472,7 +472,7 @@ static struct clk_lookup da850_clks[] = {
         CLK("spi_davinci.0",    NULL,           &spi0_clk),
         CLK("spi_davinci.1",    NULL,           &spi1_clk),
         CLK("vpif",             NULL,           &vpif_clk),
-        CLK("ahci",             NULL,           &sata_clk),
+        CLK("ahci_da850",               NULL,           &sata_clk),
         CLK("davinci-rproc.0",  NULL,           &dsp_clk),
         CLK("ehrpwm",           "fck",          &ehrpwm_clk),
         CLK("ehrpwm",           "tbclk",        &ehrpwm_tbclk),
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index 0486cdf28c8d..56ea41d5f849 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -1020,7 +1020,6 @@ int __init da8xx_register_spi_bus(int instance, unsigned num_chipselect)
 }
 
 #ifdef CONFIG_ARCH_DAVINCI_DA850
-
 static struct resource da850_sata_resources[] = {
         {
                 .start  = DA850_SATA_BASE,
@@ -1028,103 +1027,22 @@ static struct resource da850_sata_resources[] = {
                 .flags  = IORESOURCE_MEM,
         },
         {
+                .start  = DA8XX_SYSCFG1_BASE + DA8XX_PWRDN_REG,
+                .end    = DA8XX_SYSCFG1_BASE + DA8XX_PWRDN_REG + 0x3,
+                .flags  = IORESOURCE_MEM,
+        },
+        {
                 .start  = IRQ_DA850_SATAINT,
                 .flags  = IORESOURCE_IRQ,
         },
 };
 
-/* SATA PHY Control Register offset from AHCI base */
-#define SATA_P0PHYCR_REG        0x178
-
-#define SATA_PHY_MPY(x)         ((x) << 0)
-#define SATA_PHY_LOS(x)         ((x) << 6)
-#define SATA_PHY_RXCDR(x)       ((x) << 10)
-#define SATA_PHY_RXEQ(x)        ((x) << 13)
-#define SATA_PHY_TXSWING(x)     ((x) << 19)
-#define SATA_PHY_ENPLL(x)       ((x) << 31)
-
-static struct clk *da850_sata_clk;
-static unsigned long da850_sata_refclkpn;
-
-/* Supported DA850 SATA crystal frequencies */
-#define KHZ_TO_HZ(freq) ((freq) * 1000)
-static unsigned long da850_sata_xtal[] = {
-        KHZ_TO_HZ(300000),
-        KHZ_TO_HZ(250000),
-        0,                      /* Reserved */
-        KHZ_TO_HZ(187500),
-        KHZ_TO_HZ(150000),
-        KHZ_TO_HZ(125000),
-        KHZ_TO_HZ(120000),
-        KHZ_TO_HZ(100000),
-        KHZ_TO_HZ(75000),
-        KHZ_TO_HZ(60000),
-};
-
-static int da850_sata_init(struct device *dev, void __iomem *addr)
-{
-        int i, ret;
-        unsigned int val;
-
-        da850_sata_clk = clk_get(dev, NULL);
-        if (IS_ERR(da850_sata_clk))
-                return PTR_ERR(da850_sata_clk);
-
-        ret = clk_prepare_enable(da850_sata_clk);
-        if (ret)
-                goto err0;
-
-        /* Enable SATA clock receiver */
-        val = __raw_readl(DA8XX_SYSCFG1_VIRT(DA8XX_PWRDN_REG));
-        val &= ~BIT(0);
-        __raw_writel(val, DA8XX_SYSCFG1_VIRT(DA8XX_PWRDN_REG));
-
-        /* Get the multiplier needed for 1.5GHz PLL output */
-        for (i = 0; i < ARRAY_SIZE(da850_sata_xtal); i++)
-                if (da850_sata_xtal[i] == da850_sata_refclkpn)
-                        break;
-
-        if (i == ARRAY_SIZE(da850_sata_xtal)) {
-                ret = -EINVAL;
-                goto err1;
-        }
-
-        val = SATA_PHY_MPY(i + 1) |
-                SATA_PHY_LOS(1) |
-                SATA_PHY_RXCDR(4) |
-                SATA_PHY_RXEQ(1) |
-                SATA_PHY_TXSWING(3) |
-                SATA_PHY_ENPLL(1);
-
-        __raw_writel(val, addr + SATA_P0PHYCR_REG);
-
-        return 0;
-
-err1:
-        clk_disable_unprepare(da850_sata_clk);
-err0:
-        clk_put(da850_sata_clk);
-        return ret;
-}
-
-static void da850_sata_exit(struct device *dev)
-{
-        clk_disable_unprepare(da850_sata_clk);
-        clk_put(da850_sata_clk);
-}
-
-static struct ahci_platform_data da850_sata_pdata = {
-        .init   = da850_sata_init,
-        .exit   = da850_sata_exit,
-};
-
 static u64 da850_sata_dmamask = DMA_BIT_MASK(32);
 
 static struct platform_device da850_sata_device = {
-        .name   = "ahci",
+        .name   = "ahci_da850",
         .id     = -1,
         .dev    = {
-                .platform_data          = &da850_sata_pdata,
                 .dma_mask               = &da850_sata_dmamask,
                 .coherent_dma_mask      = DMA_BIT_MASK(32),
         },
@@ -1134,9 +1052,8 @@ static struct platform_device da850_sata_device = {
 
 int __init da850_register_sata(unsigned long refclkpn)
 {
-        da850_sata_refclkpn = refclkpn;
-        if (!da850_sata_refclkpn)
-                return -EINVAL;
+        /* please see comment in drivers/ata/ahci_da850.c */
+        BUG_ON(refclkpn != 100 * 1000 * 1000);
 
         return platform_device_register(&da850_sata_device);
 }
diff --git a/arch/arm/mach-imx/pm-imx6q.c b/arch/arm/mach-imx/pm-imx6q.c
index 7a9b98589db7..29e3fe6a6669 100644
--- a/arch/arm/mach-imx/pm-imx6q.c
+++ b/arch/arm/mach-imx/pm-imx6q.c
@@ -120,7 +120,7 @@ static void imx6q_enable_wb(bool enable)
 
 int imx6q_set_lpm(enum mxc_cpu_pwr_mode mode)
 {
-        struct irq_desc *iomuxc_irq_desc;
+        struct irq_data *iomuxc_irq_data = irq_get_irq_data(32);
         u32 val = readl_relaxed(ccm_base + CLPCR);
 
         val &= ~BM_CLPCR_LPM;
@@ -167,10 +167,9 @@ int imx6q_set_lpm(enum mxc_cpu_pwr_mode mode)
          * 3) Software should mask IRQ #32 right after CCM Low-Power mode
          *    is set (set bits 0-1 of CCM_CLPCR).
          */
-        iomuxc_irq_desc = irq_to_desc(32);
-        imx_gpc_irq_unmask(&iomuxc_irq_desc->irq_data);
+        imx_gpc_irq_unmask(iomuxc_irq_data);
         writel_relaxed(val, ccm_base + CLPCR);
-        imx_gpc_irq_mask(&iomuxc_irq_desc->irq_data);
+        imx_gpc_irq_mask(iomuxc_irq_data);
 
         return 0;
 }
diff --git a/arch/arm/mach-mmp/pm-mmp2.c b/arch/arm/mach-mmp/pm-mmp2.c
index 461a191a32d2..43b1a516957f 100644
--- a/arch/arm/mach-mmp/pm-mmp2.c
+++ b/arch/arm/mach-mmp/pm-mmp2.c
@@ -27,22 +27,8 @@
 
 int mmp2_set_wake(struct irq_data *d, unsigned int on)
 {
-        int irq = d->irq;
-        struct irq_desc *desc = irq_to_desc(irq);
         unsigned long data = 0;
-
-        if (unlikely(irq >= nr_irqs)) {
-                pr_err("IRQ nubmers are out of boundary!\n");
-                return -EINVAL;
-        }
-
-        if (on) {
-                if (desc->action)
-                        desc->action->flags |= IRQF_NO_SUSPEND;
-        } else {
-                if (desc->action)
-                        desc->action->flags &= ~IRQF_NO_SUSPEND;
-        }
+        int irq = d->irq;
 
         /* enable wakeup sources */
         switch (irq) {
diff --git a/arch/arm/mach-mmp/pm-pxa910.c b/arch/arm/mach-mmp/pm-pxa910.c
index 48981ca801a5..04c9daf9f8d7 100644
--- a/arch/arm/mach-mmp/pm-pxa910.c
+++ b/arch/arm/mach-mmp/pm-pxa910.c
@@ -27,22 +27,8 @@
 
 int pxa910_set_wake(struct irq_data *data, unsigned int on)
 {
-        int irq = data->irq;
-        struct irq_desc *desc = irq_to_desc(data->irq);
         uint32_t awucrm = 0, apcr = 0;
-
-        if (unlikely(irq >= nr_irqs)) {
-                pr_err("IRQ nubmers are out of boundary!\n");
-                return -EINVAL;
-        }
-
-        if (on) {
-                if (desc->action)
-                        desc->action->flags |= IRQF_NO_SUSPEND;
-        } else {
-                if (desc->action)
-                        desc->action->flags &= ~IRQF_NO_SUSPEND;
-        }
+        int irq = data->irq;
 
         /* setting wakeup sources */
         switch (irq) {
@@ -115,9 +101,11 @@ int pxa910_set_wake(struct irq_data *data, unsigned int on)
                 if (irq >= IRQ_GPIO_START && irq < IRQ_BOARD_START) {
                         awucrm = MPMU_AWUCRM_WAKEUP(2);
                         apcr |= MPMU_APCR_SLPWP2;
-                } else
+                } else {
+                        /* FIXME: This should return a proper error code ! */
                         printk(KERN_ERR "Error: no defined wake up source irq: %d\n",
                                 irq);
+                }
         }
 
         if (on) {
diff --git a/arch/arm/mach-omap1/ams-delta-fiq.c b/arch/arm/mach-omap1/ams-delta-fiq.c
index f12a12af3523..d1f12095f315 100644
--- a/arch/arm/mach-omap1/ams-delta-fiq.c
+++ b/arch/arm/mach-omap1/ams-delta-fiq.c
@@ -44,13 +44,10 @@ static unsigned int irq_counter[16];
 
 static irqreturn_t deferred_fiq(int irq, void *dev_id)
 {
-        struct irq_desc *irq_desc;
-        struct irq_chip *irq_chip = NULL;
         int gpio, irq_num, fiq_count;
+        struct irq_chip *irq_chip;
 
-        irq_desc = irq_to_desc(gpio_to_irq(AMS_DELTA_GPIO_PIN_KEYBRD_CLK));
-        if (irq_desc)
-                irq_chip = irq_desc->irq_data.chip;
+        irq_chip = irq_get_chip(gpio_to_irq(AMS_DELTA_GPIO_PIN_KEYBRD_CLK));
 
         /*
          * For each handled GPIO interrupt, keep calling its interrupt handler
diff --git a/arch/arm/mach-omap2/cclock3xxx_data.c b/arch/arm/mach-omap2/cclock3xxx_data.c
index 3b05aea56d1f..11ed9152e665 100644
--- a/arch/arm/mach-omap2/cclock3xxx_data.c
+++ b/arch/arm/mach-omap2/cclock3xxx_data.c
@@ -433,7 +433,9 @@ static const struct clk_ops dpll4_m5x2_ck_ops = {
         .enable         = &omap2_dflt_clk_enable,
         .disable        = &omap2_dflt_clk_disable,
         .is_enabled     = &omap2_dflt_clk_is_enabled,
+        .set_rate       = &omap3_clkoutx2_set_rate,
         .recalc_rate    = &omap3_clkoutx2_recalc,
+        .round_rate     = &omap3_clkoutx2_round_rate,
 };
 
 static const struct clk_ops dpll4_m5x2_ck_3630_ops = {
diff --git a/arch/arm/mach-omap2/cpuidle44xx.c b/arch/arm/mach-omap2/cpuidle44xx.c
index 4c158c838d40..01fc710c8181 100644
--- a/arch/arm/mach-omap2/cpuidle44xx.c
+++ b/arch/arm/mach-omap2/cpuidle44xx.c
@@ -23,6 +23,8 @@
 #include "prm.h"
 #include "clockdomain.h"
 
+#define MAX_CPUS        2
+
 /* Machine specific information */
 struct idle_statedata {
         u32 cpu_state;
@@ -48,11 +50,11 @@ static struct idle_statedata omap4_idle_data[] = {
         },
 };
 
-static struct powerdomain *mpu_pd, *cpu_pd[NR_CPUS];
-static struct clockdomain *cpu_clkdm[NR_CPUS];
+static struct powerdomain *mpu_pd, *cpu_pd[MAX_CPUS];
+static struct clockdomain *cpu_clkdm[MAX_CPUS];
 
 static atomic_t abort_barrier;
-static bool cpu_done[NR_CPUS];
+static bool cpu_done[MAX_CPUS];
 static struct idle_statedata *state_ptr = &omap4_idle_data[0];
 
 /* Private functions */
diff --git a/arch/arm/mach-omap2/dpll3xxx.c b/arch/arm/mach-omap2/dpll3xxx.c
index 3185ced807c9..3c418ea54bbe 100644
--- a/arch/arm/mach-omap2/dpll3xxx.c
+++ b/arch/arm/mach-omap2/dpll3xxx.c
@@ -623,6 +623,32 @@ void omap3_dpll_deny_idle(struct clk_hw_omap *clk)
 
 /* Clock control for DPLL outputs */
 
+/* Find the parent DPLL for the given clkoutx2 clock */
+static struct clk_hw_omap *omap3_find_clkoutx2_dpll(struct clk_hw *hw)
+{
+        struct clk_hw_omap *pclk = NULL;
+        struct clk *parent;
+
+        /* Walk up the parents of clk, looking for a DPLL */
+        do {
+                do {
+                        parent = __clk_get_parent(hw->clk);
+                        hw = __clk_get_hw(parent);
+                } while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC));
+                if (!hw)
+                        break;
+                pclk = to_clk_hw_omap(hw);
+        } while (pclk && !pclk->dpll_data);
+
+        /* clk does not have a DPLL as a parent?  error in the clock data */
+        if (!pclk) {
+                WARN_ON(1);
+                return NULL;
+        }
+
+        return pclk;
+}
+
 /**
  * omap3_clkoutx2_recalc - recalculate DPLL X2 output virtual clock rate
  * @clk: DPLL output struct clk
@@ -637,27 +663,14 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
         unsigned long rate;
         u32 v;
         struct clk_hw_omap *pclk = NULL;
-        struct clk *parent;
 
         if (!parent_rate)
                 return 0;
 
-        /* Walk up the parents of clk, looking for a DPLL */
-        do {
-                do {
-                        parent = __clk_get_parent(hw->clk);
-                        hw = __clk_get_hw(parent);
-                } while (hw && (__clk_get_flags(hw->clk) & CLK_IS_BASIC));
-                if (!hw)
-                        break;
-                pclk = to_clk_hw_omap(hw);
-        } while (pclk && !pclk->dpll_data);
+        pclk = omap3_find_clkoutx2_dpll(hw);
 
-        /* clk does not have a DPLL as a parent?  error in the clock data */
-        if (!pclk) {
-                WARN_ON(1);
+        if (!pclk)
                 return 0;
-        }
 
         dd = pclk->dpll_data;
 
@@ -672,6 +685,55 @@ unsigned long omap3_clkoutx2_recalc(struct clk_hw *hw,
         return rate;
 }
 
+int omap3_clkoutx2_set_rate(struct clk_hw *hw, unsigned long rate,
+                                        unsigned long parent_rate)
+{
+        return 0;
+}
+
+long omap3_clkoutx2_round_rate(struct clk_hw *hw, unsigned long rate,
+                unsigned long *prate)
+{
+        const struct dpll_data *dd;
+        u32 v;
+        struct clk_hw_omap *pclk = NULL;
+
+        if (!*prate)
+                return 0;
+
+        pclk = omap3_find_clkoutx2_dpll(hw);
+
+        if (!pclk)
+                return 0;
+
+        dd = pclk->dpll_data;
+
+        /* TYPE J does not have a clkoutx2 */
+        if (dd->flags & DPLL_J_TYPE) {
+                *prate = __clk_round_rate(__clk_get_parent(pclk->hw.clk), rate);
+                return *prate;
+        }
+
+        WARN_ON(!dd->enable_mask);
+
+        v = omap2_clk_readl(pclk, dd->control_reg) & dd->enable_mask;
+        v >>= __ffs(dd->enable_mask);
+
+        /* If in bypass, the rate is fixed to the bypass rate*/
+        if (v != OMAP3XXX_EN_DPLL_LOCKED)
+                return *prate;
+
+        if (__clk_get_flags(hw->clk) & CLK_SET_RATE_PARENT) {
+                unsigned long best_parent;
+
+                best_parent = (rate / 2);
+                *prate = __clk_round_rate(__clk_get_parent(hw->clk),
+                                best_parent);
+        }
+
+        return *prate * 2;
+}
+
 /* OMAP3/4 non-CORE DPLL clkops */
 const struct clk_hw_omap_ops clkhwops_omap3_dpll = {
         .allow_idle     = omap3_dpll_allow_idle,
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 42d81885c700..1f33f5db10d5 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1947,29 +1947,31 @@ static int _ocp_softreset(struct omap_hwmod *oh)
                 goto dis_opt_clks;
 
         _write_sysconfig(v, oh);
-        ret = _clear_softreset(oh, &v);
-        if (ret)
-                goto dis_opt_clks;
-
-        _write_sysconfig(v, oh);
 
         if (oh->class->sysc->srst_udelay)
                 udelay(oh->class->sysc->srst_udelay);
 
         c = _wait_softreset_complete(oh);
-        if (c == MAX_MODULE_SOFTRESET_WAIT)
+        if (c == MAX_MODULE_SOFTRESET_WAIT) {
                 pr_warning("omap_hwmod: %s: softreset failed (waited %d usec)\n",
                            oh->name, MAX_MODULE_SOFTRESET_WAIT);
-        else
+                ret = -ETIMEDOUT;
+                goto dis_opt_clks;
+        } else {
                 pr_debug("omap_hwmod: %s: softreset in %d usec\n", oh->name, c);
+        }
+
+        ret = _clear_softreset(oh, &v);
+        if (ret)
+                goto dis_opt_clks;
+
+        _write_sysconfig(v, oh);
 
         /*
          * XXX add _HWMOD_STATE_WEDGED for modules that don't come back from
          * _wait_target_ready() or _reset()
          */
 
-        ret = (c == MAX_MODULE_SOFTRESET_WAIT) ? -ETIMEDOUT : 0;
-
 dis_opt_clks:
         if (oh->flags & HWMOD_CONTROL_OPT_CLKS_IN_RESET)
                 _disable_optional_clocks(oh);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 18f333c440db..810c205d668b 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -1365,11 +1365,10 @@ static struct omap_hwmod_class_sysconfig dra7xx_spinlock_sysc = {
         .rev_offs       = 0x0000,
         .sysc_offs      = 0x0010,
         .syss_offs      = 0x0014,
-        .sysc_flags     = (SYSC_HAS_AUTOIDLE | SYSC_HAS_CLOCKACTIVITY |
-                           SYSC_HAS_ENAWAKEUP | SYSC_HAS_SIDLEMODE |
-                           SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
-        .idlemodes      = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-                           SIDLE_SMART_WKUP),
+        .sysc_flags     = (SYSC_HAS_AUTOIDLE | SYSC_HAS_ENAWAKEUP |
+                           SYSC_HAS_SIDLEMODE | SYSC_HAS_SOFTRESET |
+                           SYSS_HAS_RESET_STATUS),
+        .idlemodes      = (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
         .sysc_fields    = &omap_hwmod_sysc_type1,
 };
 
diff --git a/arch/arm/mach-omap2/pdata-quirks.c b/arch/arm/mach-omap2/pdata-quirks.c
index 3d5b24dcd9a4..c33e07e2f0d4 100644
--- a/arch/arm/mach-omap2/pdata-quirks.c
+++ b/arch/arm/mach-omap2/pdata-quirks.c
@@ -22,6 +22,8 @@
 #include "common-board-devices.h"
 #include "dss-common.h"
 #include "control.h"
+#include "omap-secure.h"
+#include "soc.h"
 
 struct pdata_init {
         const char *compatible;
@@ -169,6 +171,22 @@ static void __init am3517_evm_legacy_init(void)
         omap_ctrl_writel(v, AM35XX_CONTROL_IP_SW_RESET);
         omap_ctrl_readl(AM35XX_CONTROL_IP_SW_RESET); /* OCP barrier */
 }
+
+static void __init nokia_n900_legacy_init(void)
+{
+        hsmmc2_internal_input_clk();
+
+        if (omap_type() == OMAP2_DEVICE_TYPE_SEC) {
+                if (IS_ENABLED(CONFIG_ARM_ERRATA_430973)) {
+                        pr_info("RX-51: Enabling ARM errata 430973 workaround\n");
+                        /* set IBE to 1 */
+                        rx51_secure_update_aux_cr(BIT(6), 0);
+                } else {
+                        pr_warning("RX-51: Not enabling ARM errata 430973 workaround\n");
+                        pr_warning("Thumb binaries may crash randomly without this workaround\n");
+                }
+        }
+}
 #endif /* CONFIG_ARCH_OMAP3 */
 
 #ifdef CONFIG_ARCH_OMAP4
@@ -239,6 +257,7 @@ struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 #endif
 #ifdef CONFIG_ARCH_OMAP3
         OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002030, "48002030.pinmux", &pcs_pdata),
+        OF_DEV_AUXDATA("ti,omap3-padconf", 0x480025a0, "480025a0.pinmux", &pcs_pdata),
         OF_DEV_AUXDATA("ti,omap3-padconf", 0x48002a00, "48002a00.pinmux", &pcs_pdata),
         /* Only on am3517 */
         OF_DEV_AUXDATA("ti,davinci_mdio", 0x5c030000, "davinci_mdio.0", NULL),
@@ -259,7 +278,7 @@ struct of_dev_auxdata omap_auxdata_lookup[] __initdata = {
 static struct pdata_init pdata_quirks[] __initdata = {
 #ifdef CONFIG_ARCH_OMAP3
         { "compulab,omap3-sbc-t3730", omap3_sbc_t3730_legacy_init, },
-        { "nokia,omap3-n900", hsmmc2_internal_input_clk, },
+        { "nokia,omap3-n900", nokia_n900_legacy_init, },
         { "nokia,omap3-n9", hsmmc2_internal_input_clk, },
         { "nokia,omap3-n950", hsmmc2_internal_input_clk, },
         { "isee,omap3-igep0020", omap3_igep0020_legacy_init, },
diff --git a/arch/arm/mach-omap2/prminst44xx.c b/arch/arm/mach-omap2/prminst44xx.c
index 6334b96b4097..280f3c58abe5 100644
--- a/arch/arm/mach-omap2/prminst44xx.c
+++ b/arch/arm/mach-omap2/prminst44xx.c
@@ -183,11 +183,11 @@ void omap4_prminst_global_warm_sw_reset(void)
                                         OMAP4_PRM_RSTCTRL_OFFSET);
         v |= OMAP4430_RST_GLOBAL_WARM_SW_MASK;
         omap4_prminst_write_inst_reg(v, OMAP4430_PRM_PARTITION,
-                                 OMAP4430_PRM_DEVICE_INST,
+                                 dev_inst,
                                  OMAP4_PRM_RSTCTRL_OFFSET);
 
         /* OCP barrier */
         v = omap4_prminst_read_inst_reg(OMAP4430_PRM_PARTITION,
-                                    OMAP4430_PRM_DEVICE_INST,
+                                    dev_inst,
                                     OMAP4_PRM_RSTCTRL_OFFSET);
 }
diff --git a/arch/arm/mach-sa1100/include/mach/collie.h b/arch/arm/mach-sa1100/include/mach/collie.h
index f33679d2d3ee..50e1d850ee2e 100644
--- a/arch/arm/mach-sa1100/include/mach/collie.h
+++ b/arch/arm/mach-sa1100/include/mach/collie.h
@@ -13,6 +13,8 @@
 #ifndef __ASM_ARCH_COLLIE_H
 #define __ASM_ARCH_COLLIE_H
 
+#include "hardware.h" /* Gives GPIO_MAX */
+
 extern void locomolcd_power(int on);
 
 #define COLLIE_SCOOP_GPIO_BASE  (GPIO_MAX + 1)
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index 05fa505df585..f6db7dcae3f4 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -24,17 +24,21 @@ comment "Renesas ARM SoCs System Type"
 
 config ARCH_EMEV2
         bool "Emma Mobile EV2"
+        select SYS_SUPPORTS_EM_STI
 
 config ARCH_R7S72100
         bool "RZ/A1H (R7S72100)"
+        select SYS_SUPPORTS_SH_MTU2
 
 config ARCH_R8A7790
         bool "R-Car H2 (R8A77900)"
         select RENESAS_IRQC
+        select SYS_SUPPORTS_SH_CMT
 
 config ARCH_R8A7791
         bool "R-Car M2 (R8A77910)"
         select RENESAS_IRQC
+        select SYS_SUPPORTS_SH_CMT
 
 comment "Renesas ARM SoCs Board Type"
 
@@ -68,6 +72,8 @@ config ARCH_SH7372
         select ARM_CPU_SUSPEND if PM || CPU_IDLE
         select CPU_V7
         select SH_CLK_CPG
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_TMU
 
 config ARCH_SH73A0
         bool "SH-Mobile AG5 (R8A73A00)"
@@ -77,6 +83,8 @@ config ARCH_SH73A0
         select I2C
         select SH_CLK_CPG
         select RENESAS_INTC_IRQPIN
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_TMU
 
 config ARCH_R8A73A4
         bool "R-Mobile APE6 (R8A73A40)"
@@ -87,6 +95,8 @@ config ARCH_R8A73A4
         select RENESAS_IRQC
         select ARCH_HAS_CPUFREQ
         select ARCH_HAS_OPP
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_TMU
 
 config ARCH_R8A7740
         bool "R-Mobile A1 (R8A77400)"
@@ -95,6 +105,8 @@ config ARCH_R8A7740
         select CPU_V7
         select SH_CLK_CPG
         select RENESAS_INTC_IRQPIN
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_TMU
 
 config ARCH_R8A7778
         bool "R-Car M1A (R8A77781)"
@@ -104,6 +116,7 @@ config ARCH_R8A7778
         select ARM_GIC
         select USB_ARCH_HAS_EHCI
         select USB_ARCH_HAS_OHCI
+        select SYS_SUPPORTS_SH_TMU
 
 config ARCH_R8A7779
         bool "R-Car H1 (R8A77790)"
@@ -114,6 +127,7 @@ config ARCH_R8A7779
         select USB_ARCH_HAS_EHCI
         select USB_ARCH_HAS_OHCI
         select RENESAS_INTC_IRQPIN
+        select SYS_SUPPORTS_SH_TMU
 
 config ARCH_R8A7790
         bool "R-Car H2 (R8A77900)"
@@ -123,6 +137,7 @@ config ARCH_R8A7790
         select MIGHT_HAVE_PCI
         select SH_CLK_CPG
         select RENESAS_IRQC
+        select SYS_SUPPORTS_SH_CMT
 
 config ARCH_R8A7791
         bool "R-Car M2 (R8A77910)"
@@ -132,6 +147,7 @@ config ARCH_R8A7791
         select MIGHT_HAVE_PCI
         select SH_CLK_CPG
         select RENESAS_IRQC
+        select SYS_SUPPORTS_SH_CMT
 
 config ARCH_EMEV2
         bool "Emma Mobile EV2"
@@ -141,6 +157,7 @@ config ARCH_EMEV2
         select MIGHT_HAVE_PCI
         select USE_OF
         select AUTO_ZRELADDR
+        select SYS_SUPPORTS_EM_STI
 
 config ARCH_R7S72100
         bool "RZ/A1H (R7S72100)"
@@ -148,6 +165,7 @@ config ARCH_R7S72100
         select ARM_GIC
         select CPU_V7
         select SH_CLK_CPG
+        select SYS_SUPPORTS_SH_MTU2
 
 comment "Renesas ARM SoCs Board Type"
 
@@ -321,24 +339,6 @@ config SHMOBILE_TIMER_HZ
           want to select a HZ value such as 128 that can evenly divide RCLK.
           A HZ value that does not divide evenly may cause timer drift.
 
-config SH_TIMER_CMT
-        bool "CMT timer driver"
-        default y
-        help
-          This enables build of the CMT timer driver.
-
-config SH_TIMER_TMU
-        bool "TMU timer driver"
-        default y
-        help
-          This enables build of the TMU timer driver.
-
-config EM_TIMER_STI
-        bool "STI timer driver"
-        default y
-        help
-          This enables build of the STI timer driver.
-
 endmenu
 
 endif
diff --git a/arch/arm/mach-u300/Makefile b/arch/arm/mach-u300/Makefile
index 0f362b64fb87..3ec74ac95bc1 100644
--- a/arch/arm/mach-u300/Makefile
+++ b/arch/arm/mach-u300/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the linux kernel, U300 machine.
 #
 
-obj-y           := core.o timer.o
+obj-y           := core.o
 obj-m           :=
 obj-n           :=
 obj-            :=
diff --git a/arch/arm/mach-u300/timer.c b/arch/arm/mach-u300/timer.c
deleted file mode 100644
index fe08fd34c0ce..000000000000
--- a/arch/arm/mach-u300/timer.c
+++ /dev/null
@@ -1,451 +0,0 @@
-/*
- *
- * arch/arm/mach-u300/timer.c
- *
- *
- * Copyright (C) 2007-2009 ST-Ericsson AB
- * License terms: GNU General Public License (GPL) version 2
- * Timer COH 901 328, runs the OS timer interrupt.
- * Author: Linus Walleij <linus.walleij@stericsson.com>
- */
-#include <linux/interrupt.h>
-#include <linux/time.h>
-#include <linux/timex.h>
-#include <linux/clockchips.h>
-#include <linux/clocksource.h>
-#include <linux/types.h>
-#include <linux/io.h>
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/irq.h>
-#include <linux/delay.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/sched_clock.h>
-
-/* Generic stuff */
-#include <asm/mach/map.h>
-#include <asm/mach/time.h>
-
-/*
- * APP side special timer registers
- * This timer contains four timers which can fire an interrupt each.
- * OS (operating system) timer @ 32768 Hz
- * DD (device driver) timer @ 1 kHz
- * GP1 (general purpose 1) timer @ 1MHz
- * GP2 (general purpose 2) timer @ 1MHz
- */
-
-/* Reset OS Timer 32bit (-/W) */
-#define U300_TIMER_APP_ROST                                     (0x0000)
-#define U300_TIMER_APP_ROST_TIMER_RESET                         (0x00000000)
-/* Enable OS Timer 32bit (-/W) */
-#define U300_TIMER_APP_EOST                                     (0x0004)
-#define U300_TIMER_APP_EOST_TIMER_ENABLE                        (0x00000000)
-/* Disable OS Timer 32bit (-/W) */
-#define U300_TIMER_APP_DOST                                     (0x0008)
-#define U300_TIMER_APP_DOST_TIMER_DISABLE                       (0x00000000)
-/* OS Timer Mode Register 32bit (-/W) */
-#define U300_TIMER_APP_SOSTM                                    (0x000c)
-#define U300_TIMER_APP_SOSTM_MODE_CONTINUOUS                    (0x00000000)
-#define U300_TIMER_APP_SOSTM_MODE_ONE_SHOT                      (0x00000001)
-/* OS Timer Status Register 32bit (R/-) */
-#define U300_TIMER_APP_OSTS                                     (0x0010)
-#define U300_TIMER_APP_OSTS_TIMER_STATE_MASK                    (0x0000000F)
-#define U300_TIMER_APP_OSTS_TIMER_STATE_IDLE                    (0x00000001)
-#define U300_TIMER_APP_OSTS_TIMER_STATE_ACTIVE                  (0x00000002)
-#define U300_TIMER_APP_OSTS_ENABLE_IND                          (0x00000010)
-#define U300_TIMER_APP_OSTS_MODE_MASK                           (0x00000020)
-#define U300_TIMER_APP_OSTS_MODE_CONTINUOUS                     (0x00000000)
-#define U300_TIMER_APP_OSTS_MODE_ONE_SHOT                       (0x00000020)
-#define U300_TIMER_APP_OSTS_IRQ_ENABLED_IND                     (0x00000040)
-#define U300_TIMER_APP_OSTS_IRQ_PENDING_IND                     (0x00000080)
-/* OS Timer Current Count Register 32bit (R/-) */
-#define U300_TIMER_APP_OSTCC                                    (0x0014)
-/* OS Timer Terminal Count Register 32bit (R/W) */
-#define U300_TIMER_APP_OSTTC                                    (0x0018)
-/* OS Timer Interrupt Enable Register 32bit (-/W) */
-#define U300_TIMER_APP_OSTIE                                    (0x001c)
-#define U300_TIMER_APP_OSTIE_IRQ_DISABLE                        (0x00000000)
-#define U300_TIMER_APP_OSTIE_IRQ_ENABLE                         (0x00000001)
-/* OS Timer Interrupt Acknowledge Register 32bit (-/W) */
-#define U300_TIMER_APP_OSTIA                                    (0x0020)
-#define U300_TIMER_APP_OSTIA_IRQ_ACK                            (0x00000080)
-
-/* Reset DD Timer 32bit (-/W) */
-#define U300_TIMER_APP_RDDT                                     (0x0040)
-#define U300_TIMER_APP_RDDT_TIMER_RESET                         (0x00000000)
-/* Enable DD Timer 32bit (-/W) */
-#define U300_TIMER_APP_EDDT                                     (0x0044)
-#define U300_TIMER_APP_EDDT_TIMER_ENABLE                        (0x00000000)
-/* Disable DD Timer 32bit (-/W) */
-#define U300_TIMER_APP_DDDT                                     (0x0048)
-#define U300_TIMER_APP_DDDT_TIMER_DISABLE                       (0x00000000)
-/* DD Timer Mode Register 32bit (-/W) */
-#define U300_TIMER_APP_SDDTM                                    (0x004c)
-#define U300_TIMER_APP_SDDTM_MODE_CONTINUOUS                    (0x00000000)
-#define U300_TIMER_APP_SDDTM_MODE_ONE_SHOT                      (0x00000001)
-/* DD Timer Status Register 32bit (R/-) */
-#define U300_TIMER_APP_DDTS                                     (0x0050)
-#define U300_TIMER_APP_DDTS_TIMER_STATE_MASK                    (0x0000000F)
-#define U300_TIMER_APP_DDTS_TIMER_STATE_IDLE                    (0x00000001)
-#define U300_TIMER_APP_DDTS_TIMER_STATE_ACTIVE                  (0x00000002)
-#define U300_TIMER_APP_DDTS_ENABLE_IND                          (0x00000010)
-#define U300_TIMER_APP_DDTS_MODE_MASK                           (0x00000020)
-#define U300_TIMER_APP_DDTS_MODE_CONTINUOUS                     (0x00000000)
-#define U300_TIMER_APP_DDTS_MODE_ONE_SHOT                       (0x00000020)
-#define U300_TIMER_APP_DDTS_IRQ_ENABLED_IND                     (0x00000040)
-#define U300_TIMER_APP_DDTS_IRQ_PENDING_IND                     (0x00000080)
-/* DD Timer Current Count Register 32bit (R/-) */
-#define U300_TIMER_APP_DDTCC                                    (0x0054)
-/* DD Timer Terminal Count Register 32bit (R/W) */
-#define U300_TIMER_APP_DDTTC                                    (0x0058)
-/* DD Timer Interrupt Enable Register 32bit (-/W) */
-#define U300_TIMER_APP_DDTIE                                    (0x005c)
-#define U300_TIMER_APP_DDTIE_IRQ_DISABLE                        (0x00000000)
-#define U300_TIMER_APP_DDTIE_IRQ_ENABLE                         (0x00000001)
-/* DD Timer Interrupt Acknowledge Register 32bit (-/W) */
-#define U300_TIMER_APP_DDTIA                                    (0x0060)
-#define U300_TIMER_APP_DDTIA_IRQ_ACK                            (0x00000080)
-
-/* Reset GP1 Timer 32bit (-/W) */
-#define U300_TIMER_APP_RGPT1                                    (0x0080)
-#define U300_TIMER_APP_RGPT1_TIMER_RESET                        (0x00000000)
-/* Enable GP1 Timer 32bit (-/W) */
-#define U300_TIMER_APP_EGPT1                                    (0x0084)
-#define U300_TIMER_APP_EGPT1_TIMER_ENABLE                       (0x00000000)
-/* Disable GP1 Timer 32bit (-/W) */
-#define U300_TIMER_APP_DGPT1                                    (0x0088)
-#define U300_TIMER_APP_DGPT1_TIMER_DISABLE                      (0x00000000)
-/* GP1 Timer Mode Register 32bit (-/W) */
-#define U300_TIMER_APP_SGPT1M                                   (0x008c)
-#define U300_TIMER_APP_SGPT1M_MODE_CONTINUOUS                   (0x00000000)
-#define U300_TIMER_APP_SGPT1M_MODE_ONE_SHOT                     (0x00000001)
-/* GP1 Timer Status Register 32bit (R/-) */
-#define U300_TIMER_APP_GPT1S                                    (0x0090)
-#define U300_TIMER_APP_GPT1S_TIMER_STATE_MASK                   (0x0000000F)
-#define U300_TIMER_APP_GPT1S_TIMER_STATE_IDLE                   (0x00000001)
-#define U300_TIMER_APP_GPT1S_TIMER_STATE_ACTIVE                 (0x00000002)
-#define U300_TIMER_APP_GPT1S_ENABLE_IND                         (0x00000010)
-#define U300_TIMER_APP_GPT1S_MODE_MASK                          (0x00000020)
-#define U300_TIMER_APP_GPT1S_MODE_CONTINUOUS                    (0x00000000)
-#define U300_TIMER_APP_GPT1S_MODE_ONE_SHOT                      (0x00000020)
-#define U300_TIMER_APP_GPT1S_IRQ_ENABLED_IND                    (0x00000040)
-#define U300_TIMER_APP_GPT1S_IRQ_PENDING_IND                    (0x00000080)
-/* GP1 Timer Current Count Register 32bit (R/-) */
-#define U300_TIMER_APP_GPT1CC                                   (0x0094)
-/* GP1 Timer Terminal Count Register 32bit (R/W) */
-#define U300_TIMER_APP_GPT1TC                                   (0x0098)
-/* GP1 Timer Interrupt Enable Register 32bit (-/W) */
-#define U300_TIMER_APP_GPT1IE                                   (0x009c)
-#define U300_TIMER_APP_GPT1IE_IRQ_DISABLE                       (0x00000000)
-#define U300_TIMER_APP_GPT1IE_IRQ_ENABLE                        (0x00000001)
-/* GP1 Timer Interrupt Acknowledge Register 32bit (-/W) */
-#define U300_TIMER_APP_GPT1IA                                   (0x00a0)
-#define U300_TIMER_APP_GPT1IA_IRQ_ACK                           (0x00000080)
-
-/* Reset GP2 Timer 32bit (-/W) */
-#define U300_TIMER_APP_RGPT2                                    (0x00c0)
-#define U300_TIMER_APP_RGPT2_TIMER_RESET                        (0x00000000)
-/* Enable GP2 Timer 32bit (-/W) */
-#define U300_TIMER_APP_EGPT2                                    (0x00c4)
-#define U300_TIMER_APP_EGPT2_TIMER_ENABLE                       (0x00000000)
-/* Disable GP2 Timer 32bit (-/W) */
-#define U300_TIMER_APP_DGPT2                                    (0x00c8)
-#define U300_TIMER_APP_DGPT2_TIMER_DISABLE                      (0x00000000)
-/* GP2 Timer Mode Register 32bit (-/W) */
-#define U300_TIMER_APP_SGPT2M                                   (0x00cc)
-#define U300_TIMER_APP_SGPT2M_MODE_CONTINUOUS                   (0x00000000)
-#define U300_TIMER_APP_SGPT2M_MODE_ONE_SHOT                     (0x00000001)
-/* GP2 Timer Status Register 32bit (R/-) */
-#define U300_TIMER_APP_GPT2S                                    (0x00d0)
-#define U300_TIMER_APP_GPT2S_TIMER_STATE_MASK                   (0x0000000F)
-#define U300_TIMER_APP_GPT2S_TIMER_STATE_IDLE                   (0x00000001)
-#define U300_TIMER_APP_GPT2S_TIMER_STATE_ACTIVE                 (0x00000002)
-#define U300_TIMER_APP_GPT2S_ENABLE_IND                         (0x00000010)
-#define U300_TIMER_APP_GPT2S_MODE_MASK                          (0x00000020)
-#define U300_TIMER_APP_GPT2S_MODE_CONTINUOUS                    (0x00000000)
-#define U300_TIMER_APP_GPT2S_MODE_ONE_SHOT                      (0x00000020)
-#define U300_TIMER_APP_GPT2S_IRQ_ENABLED_IND                    (0x00000040)
-#define U300_TIMER_APP_GPT2S_IRQ_PENDING_IND                    (0x00000080)
-/* GP2 Timer Current Count Register 32bit (R/-) */
-#define U300_TIMER_APP_GPT2CC                                   (0x00d4)
-/* GP2 Timer Terminal Count Register 32bit (R/W) */
-#define U300_TIMER_APP_GPT2TC                                   (0x00d8)
-/* GP2 Timer Interrupt Enable Register 32bit (-/W) */
-#define U300_TIMER_APP_GPT2IE                                   (0x00dc)
-#define U300_TIMER_APP_GPT2IE_IRQ_DISABLE                       (0x00000000)
-#define U300_TIMER_APP_GPT2IE_IRQ_ENABLE                        (0x00000001)
-/* GP2 Timer Interrupt Acknowledge Register 32bit (-/W) */
-#define U300_TIMER_APP_GPT2IA                                   (0x00e0)
-#define U300_TIMER_APP_GPT2IA_IRQ_ACK                           (0x00000080)
-
-/* Clock request control register - all four timers */
-#define U300_TIMER_APP_CRC                                      (0x100)
-#define U300_TIMER_APP_CRC_CLOCK_REQUEST_ENABLE                 (0x00000001)
-
-static void __iomem *u300_timer_base;
-
-struct u300_clockevent_data {
-        struct clock_event_device cevd;
-        unsigned ticks_per_jiffy;
-};
-
-/*
- * The u300_set_mode() function is always called first, if we
- * have oneshot timer active, the oneshot scheduling function
- * u300_set_next_event() is called immediately after.
- */
-static void u300_set_mode(enum clock_event_mode mode,
-                          struct clock_event_device *evt)
-{
-        struct u300_clockevent_data *cevdata =
-                container_of(evt, struct u300_clockevent_data, cevd);
-
-        switch (mode) {
-        case CLOCK_EVT_MODE_PERIODIC:
-                /* Disable interrupts on GPT1 */
-                writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
-                       u300_timer_base + U300_TIMER_APP_GPT1IE);
-                /* Disable GP1 while we're reprogramming it. */
-                writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
-                       u300_timer_base + U300_TIMER_APP_DGPT1);
-                /*
-                 * Set the periodic mode to a certain number of ticks per
-                 * jiffy.
-                 */
-                writel(cevdata->ticks_per_jiffy,
-                       u300_timer_base + U300_TIMER_APP_GPT1TC);
-                /*
-                 * Set continuous mode, so the timer keeps triggering
-                 * interrupts.
-                 */
-                writel(U300_TIMER_APP_SGPT1M_MODE_CONTINUOUS,
-                       u300_timer_base + U300_TIMER_APP_SGPT1M);
-                /* Enable timer interrupts */
-                writel(U300_TIMER_APP_GPT1IE_IRQ_ENABLE,
-                       u300_timer_base + U300_TIMER_APP_GPT1IE);
-                /* Then enable the OS timer again */
-                writel(U300_TIMER_APP_EGPT1_TIMER_ENABLE,
-                       u300_timer_base + U300_TIMER_APP_EGPT1);
-                break;
-        case CLOCK_EVT_MODE_ONESHOT:
-                /* Just break; here? */
-                /*
-                 * The actual event will be programmed by the next event hook,
-                 * so we just set a dummy value somewhere at the end of the
-                 * universe here.
-                 */
-                /* Disable interrupts on GPT1 */
-                writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
-                       u300_timer_base + U300_TIMER_APP_GPT1IE);
-                /* Disable GP1 while we're reprogramming it. */
-                writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
-                       u300_timer_base + U300_TIMER_APP_DGPT1);
-                /*
-                 * Expire far in the future, u300_set_next_event() will be
-                 * called soon...
-                 */
-                writel(0xFFFFFFFF, u300_timer_base + U300_TIMER_APP_GPT1TC);
-                /* We run one shot per tick here! */
-                writel(U300_TIMER_APP_SGPT1M_MODE_ONE_SHOT,
-                       u300_timer_base + U300_TIMER_APP_SGPT1M);
-                /* Enable interrupts for this timer */
-                writel(U300_TIMER_APP_GPT1IE_IRQ_ENABLE,
-                       u300_timer_base + U300_TIMER_APP_GPT1IE);
-                /* Enable timer */
-                writel(U300_TIMER_APP_EGPT1_TIMER_ENABLE,
-                       u300_timer_base + U300_TIMER_APP_EGPT1);
-                break;
-        case CLOCK_EVT_MODE_UNUSED:
-        case CLOCK_EVT_MODE_SHUTDOWN:
-                /* Disable interrupts on GP1 */
-                writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
-                       u300_timer_base + U300_TIMER_APP_GPT1IE);
-                /* Disable GP1 */
-                writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
-                       u300_timer_base + U300_TIMER_APP_DGPT1);
-                break;
-        case CLOCK_EVT_MODE_RESUME:
-                /* Ignore this call */
-                break;
-        }
-}
-
-/*
- * The app timer in one shot mode obviously has to be reprogrammed
- * in EXACTLY this sequence to work properly. Do NOT try to e.g. replace
- * the interrupt disable + timer disable commands with a reset command,
- * it will fail miserably. Apparently (and I found this the hard way)
- * the timer is very sensitive to the instruction order, though you don't
- * get that impression from the data sheet.
- */
-static int u300_set_next_event(unsigned long cycles,
-                               struct clock_event_device *evt)
-
-{
-        /* Disable interrupts on GPT1 */
-        writel(U300_TIMER_APP_GPT1IE_IRQ_DISABLE,
-               u300_timer_base + U300_TIMER_APP_GPT1IE);
-        /* Disable GP1 while we're reprogramming it. */
-        writel(U300_TIMER_APP_DGPT1_TIMER_DISABLE,
-               u300_timer_base + U300_TIMER_APP_DGPT1);
-        /* Reset the General Purpose timer 1. */
-        writel(U300_TIMER_APP_RGPT1_TIMER_RESET,
-               u300_timer_base + U300_TIMER_APP_RGPT1);
-        /* IRQ in n * cycles */
-        writel(cycles, u300_timer_base + U300_TIMER_APP_GPT1TC);
-        /*
-         * We run one shot per tick here! (This is necessary to reconfigure,
-         * the timer will tilt if you don't!)
-         */
-        writel(U300_TIMER_APP_SGPT1M_MODE_ONE_SHOT,
-               u300_timer_base + U300_TIMER_APP_SGPT1M);
-        /* Enable timer interrupts */
-        writel(U300_TIMER_APP_GPT1IE_IRQ_ENABLE,
-               u300_timer_base + U300_TIMER_APP_GPT1IE);
-        /* Then enable the OS timer again */
-        writel(U300_TIMER_APP_EGPT1_TIMER_ENABLE,
-               u300_timer_base + U300_TIMER_APP_EGPT1);
-        return 0;
-}
-
-static struct u300_clockevent_data u300_clockevent_data = {
-        /* Use general purpose timer 1 as clock event */
-        .cevd = {
-                .name           = "GPT1",
-                /* Reasonably fast and accurate clock event */
-                .rating         = 300,
-                .features       = CLOCK_EVT_FEAT_PERIODIC |
-                        CLOCK_EVT_FEAT_ONESHOT,
-                .set_next_event = u300_set_next_event,
-                .set_mode       = u300_set_mode,
-        },
-};
-
-/* Clock event timer interrupt handler */
-static irqreturn_t u300_timer_interrupt(int irq, void *dev_id)
-{
-        struct clock_event_device *evt = &u300_clockevent_data.cevd;
-        /* ACK/Clear timer IRQ for the APP GPT1 Timer */
-
-        writel(U300_TIMER_APP_GPT1IA_IRQ_ACK,
-                u300_timer_base + U300_TIMER_APP_GPT1IA);
-        evt->event_handler(evt);
-        return IRQ_HANDLED;
-}
-
-static struct irqaction u300_timer_irq = {
-        .name           = "U300 Timer Tick",
-        .flags          = IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
-        .handler        = u300_timer_interrupt,
-};
-
-/*
- * Override the global weak sched_clock symbol with this
- * local implementation which uses the clocksource to get some
- * better resolution when scheduling the kernel. We accept that
- * this wraps around for now, since it is just a relative time
- * stamp. (Inspired by OMAP implementation.)
- */
-
-static u64 notrace u300_read_sched_clock(void)
-{
-        return readl(u300_timer_base + U300_TIMER_APP_GPT2CC);
-}
-
-static unsigned long u300_read_current_timer(void)
-{
-        return readl(u300_timer_base + U300_TIMER_APP_GPT2CC);
-}
-
-static struct delay_timer u300_delay_timer;
-
-/*
- * This sets up the system timers, clock source and clock event.
- */
-static void __init u300_timer_init_of(struct device_node *np)
-{
-        unsigned int irq;
-        struct clk *clk;
-        unsigned long rate;
-
-        u300_timer_base = of_iomap(np, 0);
-        if (!u300_timer_base)
-                panic("could not ioremap system timer\n");
-
-        /* Get the IRQ for the GP1 timer */
-        irq = irq_of_parse_and_map(np, 2);
-        if (!irq)
-                panic("no IRQ for system timer\n");
-
-        pr_info("U300 GP1 timer @ base: %p, IRQ: %u\n", u300_timer_base, irq);
-
-        /* Clock the interrupt controller */
-        clk = of_clk_get(np, 0);
-        BUG_ON(IS_ERR(clk));
-        clk_prepare_enable(clk);
-        rate = clk_get_rate(clk);
-
-        u300_clockevent_data.ticks_per_jiffy = DIV_ROUND_CLOSEST(rate, HZ);
-
-        sched_clock_register(u300_read_sched_clock, 32, rate);
-
-        u300_delay_timer.read_current_timer = &u300_read_current_timer;
-        u300_delay_timer.freq = rate;
-        register_current_timer_delay(&u300_delay_timer);
-
-        /*
-         * Disable the "OS" and "DD" timers - these are designed for Symbian!
-         * Example usage in cnh1601578 cpu subsystem pd_timer_app.c
-         */
-        writel(U300_TIMER_APP_CRC_CLOCK_REQUEST_ENABLE,
-                u300_timer_base + U300_TIMER_APP_CRC);
-        writel(U300_TIMER_APP_ROST_TIMER_RESET,
-                u300_timer_base + U300_TIMER_APP_ROST);
-        writel(U300_TIMER_APP_DOST_TIMER_DISABLE,
-                u300_timer_base + U300_TIMER_APP_DOST);
-        writel(U300_TIMER_APP_RDDT_TIMER_RESET,
-                u300_timer_base + U300_TIMER_APP_RDDT);
-        writel(U300_TIMER_APP_DDDT_TIMER_DISABLE,
-                u300_timer_base + U300_TIMER_APP_DDDT);
-
-        /* Reset the General Purpose timer 1. */
-        writel(U300_TIMER_APP_RGPT1_TIMER_RESET,
-                u300_timer_base + U300_TIMER_APP_RGPT1);
-
-        /* Set up the IRQ handler */
-        setup_irq(irq, &u300_timer_irq);
-
-        /* Reset the General Purpose timer 2 */
-        writel(U300_TIMER_APP_RGPT2_TIMER_RESET,
-                u300_timer_base + U300_TIMER_APP_RGPT2);
-        /* Set this timer to run around forever */
-        writel(0xFFFFFFFFU, u300_timer_base + U300_TIMER_APP_GPT2TC);
-        /* Set continuous mode so it wraps around */
-        writel(U300_TIMER_APP_SGPT2M_MODE_CONTINUOUS,
-               u300_timer_base + U300_TIMER_APP_SGPT2M);
-        /* Disable timer interrupts */
-        writel(U300_TIMER_APP_GPT2IE_IRQ_DISABLE,
-                u300_timer_base + U300_TIMER_APP_GPT2IE);
-        /* Then enable the GP2 timer to use as a free running us counter */
-        writel(U300_TIMER_APP_EGPT2_TIMER_ENABLE,
-                u300_timer_base + U300_TIMER_APP_EGPT2);
-
-        /* Use general purpose timer 2 as clock source */
-        if (clocksource_mmio_init(u300_timer_base + U300_TIMER_APP_GPT2CC,
-                        "GPT2", rate, 300, 32, clocksource_mmio_readl_up))
-                pr_err("timer: failed to initialize U300 clock source\n");
-
-        /* Configure and register the clockevent */
-        clockevents_config_and_register(&u300_clockevent_data.cevd, rate,
-                                        1, 0xffffffff);
-
-        /*
-         * TODO: init and register the rest of the timers too, they can be
-         * used by hrtimers!
-         */
-}
-
-CLOCKSOURCE_OF_DECLARE(u300_timer, "stericsson,u300-apptimer",
-                       u300_timer_init_of);
diff --git a/arch/arm/mach-zynq/Kconfig b/arch/arm/mach-zynq/Kconfig
index 6b04260aa142..f03e75bd0b2b 100644
--- a/arch/arm/mach-zynq/Kconfig
+++ b/arch/arm/mach-zynq/Kconfig
@@ -2,6 +2,8 @@ config ARCH_ZYNQ
         bool "Xilinx Zynq ARM Cortex A9 Platform" if ARCH_MULTI_V7
         select ARM_AMBA
         select ARM_GIC
+        select ARCH_HAS_CPUFREQ
+        select ARCH_HAS_OPP
         select COMMON_CLK
         select CPU_V7
         select GENERIC_CLOCKEVENTS
@@ -13,6 +15,6 @@ config ARCH_ZYNQ
         select HAVE_SMP
         select SPARSE_IRQ
         select CADENCE_TTC_TIMER
-        select ARM_GLOBAL_TIMER
+        select ARM_GLOBAL_TIMER if !CPU_FREQ
         help
           Support for Xilinx Zynq ARM Cortex A9 Platform
diff --git a/arch/arm/mach-zynq/common.c b/arch/arm/mach-zynq/common.c
index 8c09a8393fb6..a39be8e80856 100644
--- a/arch/arm/mach-zynq/common.c
+++ b/arch/arm/mach-zynq/common.c
@@ -64,6 +64,8 @@ static struct platform_device zynq_cpuidle_device = {
  */
 static void __init zynq_init_machine(void)
 {
+        struct platform_device_info devinfo = { .name = "cpufreq-cpu0", };
+
         /*
          * 64KB way size, 8-way associativity, parity disabled
          */
@@ -72,6 +74,7 @@ static void __init zynq_init_machine(void)
         of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 
         platform_device_register(&zynq_cpuidle_device);
+        platform_device_register_full(&devinfo);
 }
 
 static void __init zynq_timer_init(void)
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 2b3a56414271..ef69152f9b52 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -264,6 +264,9 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
                         note_page(st, addr, 3, pmd_val(*pmd));
                 else
                         walk_pte(st, pmd, addr);
+
+                if (SECTION_SIZE < PMD_SIZE && pmd_large(pmd[1]))
+                        note_page(st, addr + SECTION_SIZE, 3, pmd_val(pmd[1]));
         }
 }
 
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 27bbcfc7202a..516d8a7ca697 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -16,6 +16,7 @@ config ARM64
         select DCACHE_WORD_ACCESS
         select GENERIC_CLOCKEVENTS
         select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+        select GENERIC_CPU_AUTOPROBE
         select GENERIC_IOMAP
         select GENERIC_IRQ_PROBE
         select GENERIC_IRQ_SHOW
@@ -26,6 +27,7 @@ config ARM64
         select GENERIC_TIME_VSYSCALL
         select HARDIRQS_SW_RESEND
         select HAVE_ARCH_JUMP_LABEL
+        select HAVE_ARCH_KGDB
         select HAVE_ARCH_TRACEHOOK
         select HAVE_DEBUG_BUGVERBOSE
         select HAVE_DEBUG_KMEMLEAK
@@ -38,6 +40,8 @@ config ARM64
         select HAVE_MEMBLOCK
         select HAVE_PATA_PLATFORM
         select HAVE_PERF_EVENTS
+        select HAVE_PERF_REGS
+        select HAVE_PERF_USER_STACK_DUMP
         select IRQ_DOMAIN
         select MODULES_USE_ELF_RELA
         select NO_BOOTMEM
@@ -73,7 +77,7 @@ config LOCKDEP_SUPPORT
 config TRACE_IRQFLAGS_SUPPORT
         def_bool y
 
-config RWSEM_GENERIC_SPINLOCK
+config RWSEM_XCHGADD_ALGORITHM
         def_bool y
 
 config GENERIC_HWEIGHT
@@ -85,7 +89,7 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
         def_bool y
 
-config ZONE_DMA32
+config ZONE_DMA
         def_bool y
 
 config ARCH_DMA_ADDR_T_64BIT
@@ -164,6 +168,22 @@ config SMP
 
           If you don't know what to do here, say N.
 
+config SCHED_MC
+        bool "Multi-core scheduler support"
+        depends on SMP
+        help
+          Multi-core scheduler support improves the CPU scheduler's decision
+          making when dealing with multi-core CPU chips at a cost of slightly
+          increased overhead in some places. If unsure say N here.
+
+config SCHED_SMT
+        bool "SMT scheduler support"
+        depends on SMP
+        help
+          Improves the CPU scheduler's decision making when dealing with
+          MultiThreading at a cost of slightly increased overhead in some
+          places. If unsure say N here.
+
 config NR_CPUS
         int "Maximum number of CPUs (2-32)"
         range 2 32
@@ -301,6 +321,8 @@ menu "CPU Power Management"
 
 source "drivers/cpuidle/Kconfig"
 
+source "drivers/cpufreq/Kconfig"
+
 endmenu
 
 source "net/Kconfig"
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index d37d7369e260..93f4b2dd9248 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -176,6 +176,87 @@
                                 reg-names = "csr-reg";
                                 clock-output-names = "eth8clk";
                         };
+
+                        sataphy1clk: sataphy1clk@1f21c000 {
+                                compatible = "apm,xgene-device-clock";
+                                #clock-cells = <1>;
+                                clocks = <&socplldiv2 0>;
+                                reg = <0x0 0x1f21c000 0x0 0x1000>;
+                                reg-names = "csr-reg";
+                                clock-output-names = "sataphy1clk";
+                                status = "disabled";
+                                csr-offset = <0x4>;
+                                csr-mask = <0x00>;
+                                enable-offset = <0x0>;
+                                enable-mask = <0x06>;
+                        };
+
+                        sataphy2clk: sataphy1clk@1f22c000 {
+                                compatible = "apm,xgene-device-clock";
+                                #clock-cells = <1>;
+                                clocks = <&socplldiv2 0>;
+                                reg = <0x0 0x1f22c000 0x0 0x1000>;
+                                reg-names = "csr-reg";
+                                clock-output-names = "sataphy2clk";
+                                status = "ok";
+                                csr-offset = <0x4>;
+                                csr-mask = <0x3a>;
+                                enable-offset = <0x0>;
+                                enable-mask = <0x06>;
+                        };
+
+                        sataphy3clk: sataphy1clk@1f23c000 {
+                                compatible = "apm,xgene-device-clock";
+                                #clock-cells = <1>;
+                                clocks = <&socplldiv2 0>;
+                                reg = <0x0 0x1f23c000 0x0 0x1000>;
+                                reg-names = "csr-reg";
+                                clock-output-names = "sataphy3clk";
+                                status = "ok";
+                                csr-offset = <0x4>;
+                                csr-mask = <0x3a>;
+                                enable-offset = <0x0>;
+                                enable-mask = <0x06>;
+                        };
+
+                        sata01clk: sata01clk@1f21c000 {
+                                compatible = "apm,xgene-device-clock";
+                                #clock-cells = <1>;
+                                clocks = <&socplldiv2 0>;
+                                reg = <0x0 0x1f21c000 0x0 0x1000>;
+                                reg-names = "csr-reg";
+                                clock-output-names = "sata01clk";
+                                csr-offset = <0x4>;
+                                csr-mask = <0x05>;
+                                enable-offset = <0x0>;
+                                enable-mask = <0x39>;
+                        };
+
+                        sata23clk: sata23clk@1f22c000 {
+                                compatible = "apm,xgene-device-clock";
+                                #clock-cells = <1>;
+                                clocks = <&socplldiv2 0>;
+                                reg = <0x0 0x1f22c000 0x0 0x1000>;
+                                reg-names = "csr-reg";
+                                clock-output-names = "sata23clk";
+                                csr-offset = <0x4>;
+                                csr-mask = <0x05>;
+                                enable-offset = <0x0>;
+                                enable-mask = <0x39>;
+                        };
+
+                        sata45clk: sata45clk@1f23c000 {
+                                compatible = "apm,xgene-device-clock";
+                                #clock-cells = <1>;
+                                clocks = <&socplldiv2 0>;
+                                reg = <0x0 0x1f23c000 0x0 0x1000>;
+                                reg-names = "csr-reg";
+                                clock-output-names = "sata45clk";
+                                csr-offset = <0x4>;
+                                csr-mask = <0x05>;
+                                enable-offset = <0x0>;
+                                enable-mask = <0x39>;
+                        };
                 };
 
                 serial0: serial@1c020000 {
@@ -187,5 +268,76 @@
                         interrupt-parent = <&gic>;
                         interrupts = <0x0 0x4c 0x4>;
                 };
+
+                phy1: phy@1f21a000 {
+                        compatible = "apm,xgene-phy";
+                        reg = <0x0 0x1f21a000 0x0 0x100>;
+                        #phy-cells = <1>;
+                        clocks = <&sataphy1clk 0>;
+                        status = "disabled";
+                        apm,tx-boost-gain = <30 30 30 30 30 30>;
+                        apm,tx-eye-tuning = <2 10 10 2 10 10>;
+                };
+
+                phy2: phy@1f22a000 {
+                        compatible = "apm,xgene-phy";
+                        reg = <0x0 0x1f22a000 0x0 0x100>;
+                        #phy-cells = <1>;
+                        clocks = <&sataphy2clk 0>;
+                        status = "ok";
+                        apm,tx-boost-gain = <30 30 30 30 30 30>;
+                        apm,tx-eye-tuning = <1 10 10 2 10 10>;
+                };
+
+                phy3: phy@1f23a000 {
+                        compatible = "apm,xgene-phy";
+                        reg = <0x0 0x1f23a000 0x0 0x100>;
+                        #phy-cells = <1>;
+                        clocks = <&sataphy3clk 0>;
+                        status = "ok";
+                        apm,tx-boost-gain = <31 31 31 31 31 31>;
+                        apm,tx-eye-tuning = <2 10 10 2 10 10>;
+                };
+
+                sata1: sata@1a000000 {
+                        compatible = "apm,xgene-ahci";
+                        reg = <0x0 0x1a000000 0x0 0x1000>,
+                              <0x0 0x1f210000 0x0 0x1000>,
+                              <0x0 0x1f21d000 0x0 0x1000>,
+                              <0x0 0x1f21e000 0x0 0x1000>,
+                              <0x0 0x1f217000 0x0 0x1000>;
+                        interrupts = <0x0 0x86 0x4>;
+                        status = "disabled";
+                        clocks = <&sata01clk 0>;
+                        phys = <&phy1 0>;
+                        phy-names = "sata-phy";
+                };
+
+                sata2: sata@1a400000 {
+                        compatible = "apm,xgene-ahci";
+                        reg = <0x0 0x1a400000 0x0 0x1000>,
+                              <0x0 0x1f220000 0x0 0x1000>,
+                              <0x0 0x1f22d000 0x0 0x1000>,
+                              <0x0 0x1f22e000 0x0 0x1000>,
+                              <0x0 0x1f227000 0x0 0x1000>;
+                        interrupts = <0x0 0x87 0x4>;
+                        status = "ok";
+                        clocks = <&sata23clk 0>;
+                        phys = <&phy2 0>;
+                        phy-names = "sata-phy";
+                };
+
+                sata3: sata@1a800000 {
+                        compatible = "apm,xgene-ahci";
+                        reg = <0x0 0x1a800000 0x0 0x1000>,
+                              <0x0 0x1f230000 0x0 0x1000>,
+                              <0x0 0x1f23d000 0x0 0x1000>,
+                              <0x0 0x1f23e000 0x0 0x1000>;
+                        interrupts = <0x0 0x88 0x4>;
+                        status = "ok";
+                        clocks = <&sata45clk 0>;
+                        phys = <&phy3 0>;
+                        phy-names = "sata-phy";
+                };
         };
 };
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 71c53ecfcc3a..4bca4923fc0b 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -12,6 +12,7 @@ generic-y += dma.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += ftrace.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
@@ -22,13 +23,16 @@ generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += pci.h
 generic-y += poll.h
 generic-y += posix_types.h
+generic-y += preempt.h
 generic-y += resource.h
+generic-y += rwsem.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += segment.h
@@ -38,8 +42,8 @@ generic-y += shmbuf.h
 generic-y += sizes.h
 generic-y += socket.h
 generic-y += sockios.h
-generic-y += switch_to.h
 generic-y += swab.h
+generic-y += switch_to.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
@@ -49,5 +53,3 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 409ca370cfe2..66eb7648043b 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -25,6 +25,7 @@
 #define wfi()           asm volatile("wfi" : : : "memory")
 
 #define isb()           asm volatile("isb" : : : "memory")
+#define dmb(opt)        asm volatile("dmb sy" : : : "memory")
 #define dsb(opt)        asm volatile("dsb sy" : : : "memory")
 
 #define mb()            dsb()
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 889324981aa4..4c60e64a801c 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -85,6 +85,13 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 }
 
 /*
+ * Cache maintenance functions used by the DMA API. No to be used directly.
+ */
+extern void __dma_map_area(const void *, size_t, int);
+extern void __dma_unmap_area(const void *, size_t, int);
+extern void __dma_flush_range(const void *, const void *);
+
+/*
  * Copy user data from/to a page which is mapped into a different
  * processes address space.  Really, we want to allow our "user
  * space" model to handle this.
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index fda2704b3f9f..e71f81fe127a 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -228,7 +228,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
         return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (current_pt_regs()->compat_sp)
+#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
new file mode 100644
index 000000000000..cd4ac0516488
--- /dev/null
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __ASM_CPUFEATURE_H
+#define __ASM_CPUFEATURE_H
+
+#include <asm/hwcap.h>
+
+/*
+ * In the arm64 world (as in the ARM world), elf_hwcap is used both internally
+ * in the kernel and for user space to keep track of which optional features
+ * are supported by the current system. So let's map feature 'x' to HWCAP_x.
+ * Note that HWCAP_x constants are bit fields so we need to take the log.
+ */
+
+#define MAX_CPU_FEATURES        (8 * sizeof(elf_hwcap))
+#define cpu_feature(x)          ilog2(HWCAP_ ## x)
+
+static inline bool cpu_have_feature(unsigned int num)
+{
+        return elf_hwcap & (1UL << num);
+}
+
+#endif
diff --git a/arch/arm64/include/asm/debug-monitors.h b/arch/arm64/include/asm/debug-monitors.h
index 62314791570c..6e9b5b36921c 100644
--- a/arch/arm64/include/asm/debug-monitors.h
+++ b/arch/arm64/include/asm/debug-monitors.h
@@ -26,6 +26,53 @@
 #define DBG_ESR_EVT_HWWP        0x2
 #define DBG_ESR_EVT_BRK         0x6
 
+/*
+ * Break point instruction encoding
+ */
+#define BREAK_INSTR_SIZE                4
+
+/*
+ * ESR values expected for dynamic and compile time BRK instruction
+ */
+#define DBG_ESR_VAL_BRK(x)      (0xf2000000 | ((x) & 0xfffff))
+
+/*
+ * #imm16 values used for BRK instruction generation
+ * Allowed values for kgbd are 0x400 - 0x7ff
+ * 0x400: for dynamic BRK instruction
+ * 0x401: for compile time BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_IMM            0x400
+#define KDBG_COMPILED_DBG_BRK_IMM       0x401
+
+/*
+ * BRK instruction encoding
+ * The #imm16 value should be placed at bits[20:5] within BRK ins
+ */
+#define AARCH64_BREAK_MON       0xd4200000
+
+/*
+ * Extract byte from BRK instruction
+ */
+#define KGDB_DYN_DGB_BRK_INS_BYTE(x) \
+        ((((AARCH64_BREAK_MON) & 0xffe0001f) >> (x * 8)) & 0xff)
+
+/*
+ * Extract byte from BRK #imm16
+ */
+#define KGBD_DYN_DGB_BRK_IMM_BYTE(x) \
+        (((((KGDB_DYN_DGB_BRK_IMM) & 0xffff) << 5) >> (x * 8)) & 0xff)
+
+#define KGDB_DYN_DGB_BRK_BYTE(x) \
+        (KGDB_DYN_DGB_BRK_INS_BYTE(x) | KGBD_DYN_DGB_BRK_IMM_BYTE(x))
+
+#define  KGDB_DYN_BRK_INS_BYTE0  KGDB_DYN_DGB_BRK_BYTE(0)
+#define  KGDB_DYN_BRK_INS_BYTE1  KGDB_DYN_DGB_BRK_BYTE(1)
+#define  KGDB_DYN_BRK_INS_BYTE2  KGDB_DYN_DGB_BRK_BYTE(2)
+#define  KGDB_DYN_BRK_INS_BYTE3  KGDB_DYN_DGB_BRK_BYTE(3)
+
+#define CACHE_FLUSH_IS_SAFE             1
+
 enum debug_el {
         DBG_ACTIVE_EL0 = 0,
         DBG_ACTIVE_EL1,
@@ -43,23 +90,6 @@ enum debug_el {
 #ifndef __ASSEMBLY__
 struct task_struct;
 
-#define local_dbg_save(flags)                                                   \
-        do {                                                                    \
-                typecheck(unsigned long, flags);                                \
-                asm volatile(                                                   \
-                "mrs    %0, daif                        // local_dbg_save\n"    \
-                "msr    daifset, #8"                                            \
-                : "=r" (flags) : : "memory");                                   \
-        } while (0)
-
-#define local_dbg_restore(flags)                                                \
-        do {                                                                    \
-                typecheck(unsigned long, flags);                                \
-                asm volatile(                                                   \
-                "msr    daif, %0                        // local_dbg_restore\n" \
-                : : "r" (flags) : "memory");                                    \
-        } while (0)
-
 #define DBG_ARCH_ID_RESERVED    0       /* In case of ptrace ABI updates. */
 
 #define DBG_HOOK_HANDLED        0
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index fd0c0c0e447a..3a4572ec3273 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -30,6 +30,8 @@
 
 #define DMA_ERROR_CODE  (~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
+extern struct dma_map_ops coherent_swiotlb_dma_ops;
+extern struct dma_map_ops noncoherent_swiotlb_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
@@ -47,6 +49,11 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
                 return __generic_dma_ops(dev);
 }
 
+static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
+{
+        dev->archdata.dma_ops = ops;
+}
+
 #include <asm-generic/dma-mapping-common.h>
 
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h
index 6cddbb0c9f54..024c46183c3c 100644
--- a/arch/arm64/include/asm/hwcap.h
+++ b/arch/arm64/include/asm/hwcap.h
@@ -32,6 +32,12 @@
 #define COMPAT_HWCAP_IDIV       (COMPAT_HWCAP_IDIVA|COMPAT_HWCAP_IDIVT)
 #define COMPAT_HWCAP_EVTSTRM    (1 << 21)
 
+#define COMPAT_HWCAP2_AES       (1 << 0)
+#define COMPAT_HWCAP2_PMULL     (1 << 1)
+#define COMPAT_HWCAP2_SHA1      (1 << 2)
+#define COMPAT_HWCAP2_SHA2      (1 << 3)
+#define COMPAT_HWCAP2_CRC32     (1 << 4)
+
 #ifndef __ASSEMBLY__
 /*
  * This yields a mask that user programs can use to figure out what
@@ -41,7 +47,8 @@
 
 #ifdef CONFIG_COMPAT
 #define COMPAT_ELF_HWCAP        (compat_elf_hwcap)
-extern unsigned int compat_elf_hwcap;
+#define COMPAT_ELF_HWCAP2       (compat_elf_hwcap2)
+extern unsigned int compat_elf_hwcap, compat_elf_hwcap2;
 #endif
 
 extern unsigned long elf_hwcap;
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 4cc813eddacb..7846a6bb0833 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -121,7 +121,7 @@ static inline u64 __raw_readq(const volatile void __iomem *addr)
  *  I/O port access primitives.
  */
 #define IO_SPACE_LIMIT          0xffff
-#define PCI_IOBASE              ((void __iomem *)(MODULES_VADDR - SZ_2M))
+#define PCI_IOBASE              ((void __iomem *)(MODULES_VADDR - SZ_32M))
 
 static inline u8 inb(unsigned long addr)
 {
diff --git a/arch/arm64/include/asm/irqflags.h b/arch/arm64/include/asm/irqflags.h
index b2fcfbc51ecc..11cc941bd107 100644
--- a/arch/arm64/include/asm/irqflags.h
+++ b/arch/arm64/include/asm/irqflags.h
@@ -90,5 +90,28 @@ static inline int arch_irqs_disabled_flags(unsigned long flags)
         return flags & PSR_I_BIT;
 }
 
+/*
+ * save and restore debug state
+ */
+#define local_dbg_save(flags)                                           \
+        do {                                                            \
+                typecheck(unsigned long, flags);                        \
+                asm volatile(                                           \
+                "mrs    %0, daif                // local_dbg_save\n"    \
+                "msr    daifset, #8"                                    \
+                : "=r" (flags) : : "memory");                           \
+        } while (0)
+
+#define local_dbg_restore(flags)                                        \
+        do {                                                            \
+                typecheck(unsigned long, flags);                        \
+                asm volatile(                                           \
+                "msr    daif, %0                // local_dbg_restore\n" \
+                : : "r" (flags) : "memory");                            \
+        } while (0)
+
+#define local_dbg_enable()      asm("msr        daifclr, #8" : : : "memory")
+#define local_dbg_disable()     asm("msr        daifset, #8" : : : "memory")
+
 #endif
 #endif
diff --git a/arch/arm64/include/asm/kgdb.h b/arch/arm64/include/asm/kgdb.h
new file mode 100644
index 000000000000..3c8aafc1082f
--- /dev/null
+++ b/arch/arm64/include/asm/kgdb.h
@@ -0,0 +1,84 @@
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/include/kgdb.h
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ARM_KGDB_H
+#define __ARM_KGDB_H
+
+#include <linux/ptrace.h>
+#include <asm/debug-monitors.h>
+
+#ifndef __ASSEMBLY__
+
+static inline void arch_kgdb_breakpoint(void)
+{
+        asm ("brk %0" : : "I" (KDBG_COMPILED_DBG_BRK_IMM));
+}
+
+extern void kgdb_handle_bus_error(void);
+extern int kgdb_fault_expected;
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * gdb is expecting the following registers layout.
+ *
+ * General purpose regs:
+ *     r0-r30: 64 bit
+ *     sp,pc : 64 bit
+ *     pstate  : 64 bit
+ *     Total: 34
+ * FPU regs:
+ *     f0-f31: 128 bit
+ *     Total: 32
+ * Extra regs
+ *     fpsr & fpcr: 32 bit
+ *     Total: 2
+ *
+ */
+
+#define _GP_REGS                34
+#define _FP_REGS                32
+#define _EXTRA_REGS             2
+/*
+ * general purpose registers size in bytes.
+ * pstate is only 4 bytes. subtract 4 bytes
+ */
+#define GP_REG_BYTES            (_GP_REGS * 8)
+#define DBG_MAX_REG_NUM         (_GP_REGS + _FP_REGS + _EXTRA_REGS)
+
+/*
+ * Size of I/O buffer for gdb packet.
+ * considering to hold all register contents, size is set
+ */
+
+#define BUFMAX                  2048
+
+/*
+ * Number of bytes required for gdb_regs buffer.
+ * _GP_REGS: 8 bytes, _FP_REGS: 16 bytes and _EXTRA_REGS: 4 bytes each
+ * GDB fails to connect for size beyond this with error
+ * "'g' packet reply is too long"
+ */
+
+#define NUMREGBYTES     ((_GP_REGS * 8) + (_FP_REGS * 16) + \
+                        (_EXTRA_REGS * 4))
+
+#endif /* __ASM_KGDB_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 0eb398655378..21ef48d32ff2 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -106,7 +106,6 @@
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_PS_MASK        (7 << 16)
-#define VTCR_EL2_PS_40B         (2 << 16)
 #define VTCR_EL2_TG0_MASK       (1 << 14)
 #define VTCR_EL2_TG0_4K         (0 << 14)
 #define VTCR_EL2_TG0_64K        (1 << 14)
@@ -129,10 +128,9 @@
  * 64kB pages (TG0 = 1)
  * 2 level page tables (SL = 1)
  */
-#define VTCR_EL2_FLAGS          (VTCR_EL2_PS_40B | VTCR_EL2_TG0_64K | \
-                                 VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
-                                 VTCR_EL2_IRGN0_WBWA | VTCR_EL2_SL0_LVL1 | \
-                                 VTCR_EL2_T0SZ_40B)
+#define VTCR_EL2_FLAGS          (VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \
+                                 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+                                 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
 #define VTTBR_X         (38 - VTCR_EL2_T0SZ_40B)
 #else
 /*
@@ -142,10 +140,9 @@
  * 4kB pages (TG0 = 0)
  * 3 level page tables (SL = 1)
  */
-#define VTCR_EL2_FLAGS          (VTCR_EL2_PS_40B | VTCR_EL2_TG0_4K | \
-                                 VTCR_EL2_SH0_INNER | VTCR_EL2_ORGN0_WBWA | \
-                                 VTCR_EL2_IRGN0_WBWA | VTCR_EL2_SL0_LVL1 | \
-                                 VTCR_EL2_T0SZ_40B)
+#define VTCR_EL2_FLAGS          (VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
+                                 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
+                                 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
 #define VTTBR_X         (37 - VTCR_EL2_T0SZ_40B)
 #endif
 
diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h
index 13fb0b3efc5f..453a179469a3 100644
--- a/arch/arm64/include/asm/percpu.h
+++ b/arch/arm64/include/asm/percpu.h
@@ -16,6 +16,8 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#ifdef CONFIG_SMP
+
 static inline void set_my_cpu_offset(unsigned long off)
 {
         asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -36,6 +38,12 @@ static inline unsigned long __my_cpu_offset(void)
 }
 #define __my_cpu_offset __my_cpu_offset()
 
+#else   /* !CONFIG_SMP */
+
+#define set_my_cpu_offset(x)    do { } while (0)
+
+#endif /* CONFIG_SMP */
+
 #include <asm-generic/percpu.h>
 
 #endif /* __ASM_PERCPU_H */
diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h
index b1d2e26c3c88..f7af66b54cb2 100644
--- a/arch/arm64/include/asm/pgtable-hwdef.h
+++ b/arch/arm64/include/asm/pgtable-hwdef.h
@@ -100,9 +100,9 @@
 #define PTE_HYP                 PTE_USER
 
 /*
- * 40-bit physical address supported.
+ * Highest possible physical address supported.
  */
-#define PHYS_MASK_SHIFT         (40)
+#define PHYS_MASK_SHIFT         (48)
 #define PHYS_MASK               ((UL(1) << PHYS_MASK_SHIFT) - 1)
 
 /*
@@ -122,7 +122,6 @@
 #define TCR_SHARED              ((UL(3) << 12) | (UL(3) << 28))
 #define TCR_TG0_64K             (UL(1) << 14)
 #define TCR_TG1_64K             (UL(1) << 30)
-#define TCR_IPS_40BIT           (UL(2) << 32)
 #define TCR_ASID16              (UL(1) << 36)
 #define TCR_TBI0                (UL(1) << 37)
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index b524dcd17243..90c811f05a2e 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -136,11 +136,11 @@ extern struct page *empty_zero_page;
 /*
  * The following only work if pte_present(). Undefined behaviour otherwise.
  */
-#define pte_present(pte)        (pte_val(pte) & (PTE_VALID | PTE_PROT_NONE))
-#define pte_dirty(pte)          (pte_val(pte) & PTE_DIRTY)
-#define pte_young(pte)          (pte_val(pte) & PTE_AF)
-#define pte_special(pte)        (pte_val(pte) & PTE_SPECIAL)
-#define pte_write(pte)          (pte_val(pte) & PTE_WRITE)
+#define pte_present(pte)        (!!(pte_val(pte) & (PTE_VALID | PTE_PROT_NONE)))
+#define pte_dirty(pte)          (!!(pte_val(pte) & PTE_DIRTY))
+#define pte_young(pte)          (!!(pte_val(pte) & PTE_AF))
+#define pte_special(pte)        (!!(pte_val(pte) & PTE_SPECIAL))
+#define pte_write(pte)          (!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)           (!(pte_val(pte) & PTE_UXN))
 
 #define pte_valid_user(pte) \
@@ -199,7 +199,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
                               pte_t *ptep, pte_t pte)
 {
         if (pte_valid_user(pte)) {
-                if (pte_exec(pte))
+                if (!pte_special(pte) && pte_exec(pte))
                         __sync_icache_dcache(pte, addr);
                 if (pte_dirty(pte) && pte_write(pte))
                         pte_val(pte) &= ~PTE_RDONLY;
@@ -227,36 +227,36 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_PTE_SPECIAL
 
-/*
- * Software PMD bits for THP
- */
+static inline pte_t pmd_pte(pmd_t pmd)
+{
+        return __pte(pmd_val(pmd));
+}
 
-#define PMD_SECT_DIRTY          (_AT(pmdval_t, 1) << 55)
-#define PMD_SECT_SPLITTING      (_AT(pmdval_t, 1) << 57)
+static inline pmd_t pte_pmd(pte_t pte)
+{
+        return __pmd(pte_val(pte));
+}
 
 /*
  * THP definitions.
  */
-#define pmd_young(pmd)          (pmd_val(pmd) & PMD_SECT_AF)
-
-#define __HAVE_ARCH_PMD_WRITE
-#define pmd_write(pmd)          (!(pmd_val(pmd) & PMD_SECT_RDONLY))
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)     (pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
-#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
+#define pmd_trans_splitting(pmd)        pte_special(pmd_pte(pmd))
 #endif
 
-#define PMD_BIT_FUNC(fn,op) \
-static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
+#define pmd_young(pmd)          pte_young(pmd_pte(pmd))
+#define pmd_wrprotect(pmd)      pte_pmd(pte_wrprotect(pmd_pte(pmd)))
+#define pmd_mksplitting(pmd)    pte_pmd(pte_mkspecial(pmd_pte(pmd)))
+#define pmd_mkold(pmd)          pte_pmd(pte_mkold(pmd_pte(pmd)))
+#define pmd_mkwrite(pmd)        pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkdirty(pmd)        pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkyoung(pmd)        pte_pmd(pte_mkyoung(pmd_pte(pmd)))
+#define pmd_mknotpresent(pmd)   (__pmd(pmd_val(pmd) &= ~PMD_TYPE_MASK))
 
-PMD_BIT_FUNC(wrprotect, |= PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkold,     &= ~PMD_SECT_AF);
-PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
-PMD_BIT_FUNC(mkwrite,   &= ~PMD_SECT_RDONLY);
-PMD_BIT_FUNC(mkdirty,   |= PMD_SECT_DIRTY);
-PMD_BIT_FUNC(mkyoung,   |= PMD_SECT_AF);
-PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK);
+#define __HAVE_ARCH_PMD_WRITE
+#define pmd_write(pmd)          pte_write(pmd_pte(pmd))
 
 #define pmd_mkhuge(pmd)         (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
 
@@ -266,15 +266,6 @@ PMD_BIT_FUNC(mknotpresent, &= ~PMD_TYPE_MASK);
 
 #define pmd_page(pmd)           pfn_to_page(__phys_to_pfn(pmd_val(pmd) & PHYS_MASK))
 
-static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
-{
-        const pmdval_t mask = PMD_SECT_USER | PMD_SECT_PXN | PMD_SECT_UXN |
-                              PMD_SECT_RDONLY | PMD_SECT_PROT_NONE |
-                              PMD_SECT_VALID;
-        pmd_val(pmd) = (pmd_val(pmd) & ~mask) | (pgprot_val(newprot) & mask);
-        return pmd;
-}
-
 #define set_pmd_at(mm, addr, pmdp, pmd) set_pmd(pmdp, pmd)
 
 static inline int has_transparent_hugepage(void)
@@ -286,11 +277,9 @@ static inline int has_transparent_hugepage(void)
  * Mark the prot value as uncacheable and unbufferable.
  */
 #define pgprot_noncached(prot) \
-        __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE))
+        __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN)
 #define pgprot_writecombine(prot) \
-        __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
-#define pgprot_dmacoherent(prot) \
-        __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC))
+        __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN)
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
@@ -383,6 +372,11 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
         return pte;
 }
 
+static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
+{
+        return pte_pmd(pte_modify(pmd_pte(pmd), newprot));
+}
+
 extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 extern pgd_t idmap_pg_dir[PTRS_PER_PGD];
 
diff --git a/arch/arm64/include/asm/psci.h b/arch/arm64/include/asm/psci.h
index e5312ea0ec1a..d15ab8b46336 100644
--- a/arch/arm64/include/asm/psci.h
+++ b/arch/arm64/include/asm/psci.h
@@ -14,6 +14,6 @@
 #ifndef __ASM_PSCI_H
 #define __ASM_PSCI_H
 
-int psci_init(void);
+void psci_init(void);
 
 #endif /* __ASM_PSCI_H */
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 0e7fa4963735..c7ba261dd4b3 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -68,6 +68,7 @@
 
 /* Architecturally defined mapping between AArch32 and AArch64 registers */
 #define compat_usr(x)   regs[(x)]
+#define compat_fp       regs[11]
 #define compat_sp       regs[13]
 #define compat_lr       regs[14]
 #define compat_sp_hyp   regs[15]
@@ -132,7 +133,7 @@ struct pt_regs {
         (!((regs)->pstate & PSR_F_BIT))
 
 #define user_stack_pointer(regs) \
-        ((regs)->sp)
+        (!compat_user_mode(regs)) ? ((regs)->sp) : ((regs)->compat_sp)
 
 /*
  * Are the current registers suitable for user mode? (used to maintain
@@ -164,7 +165,7 @@ static inline int valid_user_regs(struct user_pt_regs *regs)
         return 0;
 }
 
-#define instruction_pointer(regs)       (regs)->pc
+#define instruction_pointer(regs)       ((unsigned long)(regs)->pc)
 
 #ifdef CONFIG_SMP
 extern unsigned long profile_pc(struct pt_regs *regs);
diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
index 717031a762c2..72cadf52ca80 100644
--- a/arch/arm64/include/asm/tlb.h
+++ b/arch/arm64/include/asm/tlb.h
@@ -19,115 +19,44 @@
 #ifndef __ASM_TLB_H
 #define __ASM_TLB_H
 
-#include <linux/pagemap.h>
-#include <linux/swap.h>
 
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-
-#define MMU_GATHER_BUNDLE       8
-
-/*
- * TLB handling.  This allows us to remove pages from the page
- * tables, and efficiently handle the TLB issues.
- */
-struct mmu_gather {
-        struct mm_struct        *mm;
-        unsigned int            fullmm;
-        struct vm_area_struct   *vma;
-        unsigned long           start, end;
-        unsigned long           range_start;
-        unsigned long           range_end;
-        unsigned int            nr;
-        unsigned int            max;
-        struct page             **pages;
-        struct page             *local[MMU_GATHER_BUNDLE];
-};
+#include <asm-generic/tlb.h>
 
 /*
- * This is unnecessarily complex.  There's three ways the TLB shootdown
- * code is used:
+ * There's three ways the TLB shootdown code is used:
  *  1. Unmapping a range of vmas.  See zap_page_range(), unmap_region().
  *     tlb->fullmm = 0, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.
  *  2. Unmapping all vmas.  See exit_mmap().
  *     tlb->fullmm = 1, and tlb_start_vma/tlb_end_vma will be called.
- *     tlb->vma will be non-NULL.  Additionally, page tables will be freed.
+ *     Page tables will be freed.
  *  3. Unmapping argument pages.  See shift_arg_pages().
  *     tlb->fullmm = 0, but tlb_start_vma/tlb_end_vma will not be called.
- *     tlb->vma will be NULL.
  */
 static inline void tlb_flush(struct mmu_gather *tlb)
 {
-        if (tlb->fullmm || !tlb->vma)
+        if (tlb->fullmm) {
                 flush_tlb_mm(tlb->mm);
-        else if (tlb->range_end > 0) {
-                flush_tlb_range(tlb->vma, tlb->range_start, tlb->range_end);
-                tlb->range_start = TASK_SIZE;
-                tlb->range_end = 0;
+        } else if (tlb->end > 0) {
+                struct vm_area_struct vma = { .vm_mm = tlb->mm, };
+                flush_tlb_range(&vma, tlb->start, tlb->end);
+                tlb->start = TASK_SIZE;
+                tlb->end = 0;
         }
 }
 
 static inline void tlb_add_flush(struct mmu_gather *tlb, unsigned long addr)
 {
         if (!tlb->fullmm) {
-                if (addr < tlb->range_start)
-                        tlb->range_start = addr;
-                if (addr + PAGE_SIZE > tlb->range_end)
-                        tlb->range_end = addr + PAGE_SIZE;
-        }
-}
-
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-        unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
-
-        if (addr) {
-                tlb->pages = (void *)addr;
-                tlb->max = PAGE_SIZE / sizeof(struct page *);
+                tlb->start = min(tlb->start, addr);
+                tlb->end = max(tlb->end, addr + PAGE_SIZE);
         }
 }
 
-static inline void tlb_flush_mmu(struct mmu_gather *tlb)
-{
-        tlb_flush(tlb);
-        free_pages_and_swap_cache(tlb->pages, tlb->nr);
-        tlb->nr = 0;
-        if (tlb->pages == tlb->local)
-                __tlb_alloc_page(tlb);
-}
-
-static inline void
-tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long start, unsigned long end)
-{
-        tlb->mm = mm;
-        tlb->fullmm = !(start | (end+1));
-        tlb->start = start;
-        tlb->end = end;
-        tlb->vma = NULL;
-        tlb->max = ARRAY_SIZE(tlb->local);
-        tlb->pages = tlb->local;
-        tlb->nr = 0;
-        __tlb_alloc_page(tlb);
-}
-
-static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-        tlb_flush_mmu(tlb);
-
-        /* keep the page table cache within bounds */
-        check_pgt_cache();
-
-        if (tlb->pages != tlb->local)
-                free_pages((unsigned long)tlb->pages, 0);
-}
-
 /*
  * Memorize the range for the TLB flush.
  */
-static inline void
-tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
+static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
+                                          unsigned long addr)
 {
         tlb_add_flush(tlb, addr);
 }
@@ -137,38 +66,24 @@ tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep, unsigned long addr)
  * case where we're doing a full MM flush.  When we're doing a munmap,
  * the vmas are adjusted to only cover the region to be torn down.
  */
-static inline void
-tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+static inline void tlb_start_vma(struct mmu_gather *tlb,
+                                 struct vm_area_struct *vma)
 {
         if (!tlb->fullmm) {
-                tlb->vma = vma;
-                tlb->range_start = TASK_SIZE;
-                tlb->range_end = 0;
+                tlb->start = TASK_SIZE;
+                tlb->end = 0;
         }
 }
 
-static inline void
-tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
+static inline void tlb_end_vma(struct mmu_gather *tlb,
+                               struct vm_area_struct *vma)
 {
         if (!tlb->fullmm)
                 tlb_flush(tlb);
 }
 
-static inline int __tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-        tlb->pages[tlb->nr++] = page;
-        VM_BUG_ON(tlb->nr > tlb->max);
-        return tlb->max - tlb->nr;
-}
-
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-        if (!__tlb_remove_page(tlb, page))
-                tlb_flush_mmu(tlb);
-}
-
 static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
-        unsigned long addr)
+                                  unsigned long addr)
 {
         pgtable_page_dtor(pte);
         tlb_add_flush(tlb, addr);
@@ -184,16 +99,5 @@ static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmdp,
 }
 #endif
 
-#define pte_free_tlb(tlb, ptep, addr)   __pte_free_tlb(tlb, ptep, addr)
-#define pmd_free_tlb(tlb, pmdp, addr)   __pmd_free_tlb(tlb, pmdp, addr)
-#define pud_free_tlb(tlb, pudp, addr)   pud_free((tlb)->mm, pudp)
-
-#define tlb_migrate_finish(mm)          do { } while (0)
-
-static inline void
-tlb_remove_pmd_tlb_entry(struct mmu_gather *tlb, pmd_t *pmdp, unsigned long addr)
-{
-        tlb_add_flush(tlb, addr);
-}
 
 #endif
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
new file mode 100644
index 000000000000..0172e6d76bf3
--- /dev/null
+++ b/arch/arm64/include/asm/topology.h
@@ -0,0 +1,39 @@
+#ifndef __ASM_TOPOLOGY_H
+#define __ASM_TOPOLOGY_H
+
+#ifdef CONFIG_SMP
+
+#include <linux/cpumask.h>
+
+struct cpu_topology {
+        int thread_id;
+        int core_id;
+        int cluster_id;
+        cpumask_t thread_sibling;
+        cpumask_t core_sibling;
+};
+
+extern struct cpu_topology cpu_topology[NR_CPUS];
+
+#define topology_physical_package_id(cpu)       (cpu_topology[cpu].cluster_id)
+#define topology_core_id(cpu)           (cpu_topology[cpu].core_id)
+#define topology_core_cpumask(cpu)      (&cpu_topology[cpu].core_sibling)
+#define topology_thread_cpumask(cpu)    (&cpu_topology[cpu].thread_sibling)
+
+#define mc_capable()    (cpu_topology[0].cluster_id != -1)
+#define smt_capable()   (cpu_topology[0].thread_id != -1)
+
+void init_cpu_topology(void);
+void store_cpu_topology(unsigned int cpuid);
+const struct cpumask *cpu_coregroup_mask(int cpu);
+
+#else
+
+static inline void init_cpu_topology(void) { }
+static inline void store_cpu_topology(unsigned int cpuid) { }
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_ARM_TOPOLOGY_H */
diff --git a/arch/arm64/include/asm/uaccess.h b/arch/arm64/include/asm/uaccess.h
index 6c0f684aca81..3bf8f4e99a51 100644
--- a/arch/arm64/include/asm/uaccess.h
+++ b/arch/arm64/include/asm/uaccess.h
@@ -83,7 +83,7 @@ static inline void set_fs(mm_segment_t fs)
  * Returns 1 if the range is valid, 0 otherwise.
  *
  * This is equivalent to the following test:
- * (u65)addr + (u65)size < (u65)current->addr_limit
+ * (u65)addr + (u65)size <= current->addr_limit
  *
  * This needs 65-bit arithmetic.
  */
@@ -91,7 +91,7 @@ static inline void set_fs(mm_segment_t fs)
 ({                                                                      \
         unsigned long flag, roksum;                                     \
         __chk_user_ptr(addr);                                           \
-        asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, cc"         \
+        asm("adds %1, %1, %3; ccmp %1, %4, #2, cc; cset %0, ls"         \
                 : "=&r" (flag), "=&r" (roksum)                          \
                 : "1" (addr), "Ir" (size),                              \
                   "r" (current_thread_info()->addr_limit)               \
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index 82ce217e94cf..a4654c656a1e 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -14,6 +14,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 #ifdef CONFIG_COMPAT
+#define __ARCH_WANT_COMPAT_SYS_GETDENTS64
 #define __ARCH_WANT_COMPAT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
diff --git a/arch/arm64/include/uapi/asm/Kbuild b/arch/arm64/include/uapi/asm/Kbuild
index e4b78bdca19e..942376d37d22 100644
--- a/arch/arm64/include/uapi/asm/Kbuild
+++ b/arch/arm64/include/uapi/asm/Kbuild
@@ -9,6 +9,7 @@ header-y += byteorder.h
 header-y += fcntl.h
 header-y += hwcap.h
 header-y += kvm_para.h
+header-y += perf_regs.h
 header-y += param.h
 header-y += ptrace.h
 header-y += setup.h
diff --git a/arch/arm64/include/uapi/asm/perf_regs.h b/arch/arm64/include/uapi/asm/perf_regs.h
new file mode 100644
index 000000000000..172b8317ee49
--- /dev/null
+++ b/arch/arm64/include/uapi/asm/perf_regs.h
@@ -0,0 +1,40 @@
+#ifndef _ASM_ARM64_PERF_REGS_H
+#define _ASM_ARM64_PERF_REGS_H
+
+enum perf_event_arm_regs {
+        PERF_REG_ARM64_X0,
+        PERF_REG_ARM64_X1,
+        PERF_REG_ARM64_X2,
+        PERF_REG_ARM64_X3,
+        PERF_REG_ARM64_X4,
+        PERF_REG_ARM64_X5,
+        PERF_REG_ARM64_X6,
+        PERF_REG_ARM64_X7,
+        PERF_REG_ARM64_X8,
+        PERF_REG_ARM64_X9,
+        PERF_REG_ARM64_X10,
+        PERF_REG_ARM64_X11,
+        PERF_REG_ARM64_X12,
+        PERF_REG_ARM64_X13,
+        PERF_REG_ARM64_X14,
+        PERF_REG_ARM64_X15,
+        PERF_REG_ARM64_X16,
+        PERF_REG_ARM64_X17,
+        PERF_REG_ARM64_X18,
+        PERF_REG_ARM64_X19,
+        PERF_REG_ARM64_X20,
+        PERF_REG_ARM64_X21,
+        PERF_REG_ARM64_X22,
+        PERF_REG_ARM64_X23,
+        PERF_REG_ARM64_X24,
+        PERF_REG_ARM64_X25,
+        PERF_REG_ARM64_X26,
+        PERF_REG_ARM64_X27,
+        PERF_REG_ARM64_X28,
+        PERF_REG_ARM64_X29,
+        PERF_REG_ARM64_LR,
+        PERF_REG_ARM64_SP,
+        PERF_REG_ARM64_PC,
+        PERF_REG_ARM64_MAX,
+};
+#endif /* _ASM_ARM64_PERF_REGS_H */
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 2d4554b13410..7d811d9522bc 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -14,12 +14,14 @@ arm64-obj-y		:= cputable.o debug-monitors.o entry.o irq.o fpsimd.o	\
 arm64-obj-$(CONFIG_COMPAT)              += sys32.o kuser32.o signal32.o         \
                                            sys_compat.o
 arm64-obj-$(CONFIG_MODULES)             += arm64ksyms.o module.o
-arm64-obj-$(CONFIG_SMP)                 += smp.o smp_spin_table.o
+arm64-obj-$(CONFIG_SMP)                 += smp.o smp_spin_table.o topology.o
+arm64-obj-$(CONFIG_PERF_EVENTS)         += perf_regs.o
 arm64-obj-$(CONFIG_HW_PERF_EVENTS)      += perf_event.o
-arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)+= hw_breakpoint.o
+arm64-obj-$(CONFIG_HAVE_HW_BREAKPOINT)  += hw_breakpoint.o
 arm64-obj-$(CONFIG_EARLY_PRINTK)        += early_printk.o
 arm64-obj-$(CONFIG_ARM64_CPU_SUSPEND)   += sleep.o suspend.o
 arm64-obj-$(CONFIG_JUMP_LABEL)          += jump_label.o
+arm64-obj-$(CONFIG_KGDB)                += kgdb.o
 
 obj-y                                   += $(arm64-obj-y) vdso/
 obj-m                                   += $(arm64-obj-m)
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 636ba8b6240b..14ba23c61153 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -137,7 +137,6 @@ void disable_debug_monitors(enum debug_el el)
 static void clear_os_lock(void *unused)
 {
         asm volatile("msr oslar_el1, %0" : : "r" (0));
-        isb();
 }
 
 static int os_lock_notify(struct notifier_block *self,
@@ -156,8 +155,9 @@ static struct notifier_block os_lock_nb = {
 static int debug_monitors_init(void)
 {
         /* Clear the OS lock. */
-        smp_call_function(clear_os_lock, NULL, 1);
-        clear_os_lock(NULL);
+        on_each_cpu(clear_os_lock, NULL, 1);
+        isb();
+        local_dbg_enable();
 
         /* Register hotplug handler. */
         register_cpu_notifier(&os_lock_nb);
@@ -189,7 +189,7 @@ static void clear_regs_spsr_ss(struct pt_regs *regs)
 
 /* EL1 Single Step Handler hooks */
 static LIST_HEAD(step_hook);
-DEFINE_RWLOCK(step_hook_lock);
+static DEFINE_RWLOCK(step_hook_lock);
 
 void register_step_hook(struct step_hook *hook)
 {
@@ -276,7 +276,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
  * Use reader/writer locks instead of plain spinlock.
  */
 static LIST_HEAD(break_hook);
-DEFINE_RWLOCK(break_hook_lock);
+static DEFINE_RWLOCK(break_hook_lock);
 
 void register_break_hook(struct break_hook *hook)
 {
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 0b281fffda51..61035d6814cb 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -384,26 +384,18 @@ ENDPROC(__calc_phys_offset)
  * Preserves:   tbl, flags
  * Corrupts:    phys, start, end, pstate
  */
-        .macro  create_block_map, tbl, flags, phys, start, end, idmap=0
+        .macro  create_block_map, tbl, flags, phys, start, end
         lsr     \phys, \phys, #BLOCK_SHIFT
-        .if     \idmap
-        and     \start, \phys, #PTRS_PER_PTE - 1        // table index
-        .else
         lsr     \start, \start, #BLOCK_SHIFT
         and     \start, \start, #PTRS_PER_PTE - 1       // table index
-        .endif
         orr     \phys, \flags, \phys, lsl #BLOCK_SHIFT  // table entry
-        .ifnc   \start,\end
         lsr     \end, \end, #BLOCK_SHIFT
         and     \end, \end, #PTRS_PER_PTE - 1           // table end index
-        .endif
 9999:   str     \phys, [\tbl, \start, lsl #3]           // store the entry
-        .ifnc   \start,\end
         add     \start, \start, #1                      // next entry
         add     \phys, \phys, #BLOCK_SIZE               // next block
         cmp     \start, \end
         b.ls    9999b
-        .endif
         .endm
 
 /*
@@ -435,9 +427,13 @@ __create_page_tables:
          * Create the identity mapping.
          */
         add     x0, x25, #PAGE_SIZE             // section table address
-        adr     x3, __turn_mmu_on               // virtual/physical address
+        ldr     x3, =KERNEL_START
+        add     x3, x3, x28                     // __pa(KERNEL_START)
         create_pgd_entry x25, x0, x3, x5, x6
-        create_block_map x0, x7, x3, x5, x5, idmap=1
+        ldr     x6, =KERNEL_END
+        mov     x5, x3                          // __pa(KERNEL_START)
+        add     x6, x6, x28                     // __pa(KERNEL_END)
+        create_block_map x0, x7, x3, x5, x6
 
         /*
          * Map the kernel image (starting with PHYS_OFFSET).
@@ -445,7 +441,7 @@ __create_page_tables:
         add     x0, x26, #PAGE_SIZE             // section table address
         mov     x5, #PAGE_OFFSET
         create_pgd_entry x26, x0, x5, x3, x6
-        ldr     x6, =KERNEL_END - 1
+        ldr     x6, =KERNEL_END
         mov     x3, x24                         // phys offset
         create_block_map x0, x7, x3, x5, x6
 
diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c
new file mode 100644
index 000000000000..75c9cf1aafee
--- /dev/null
+++ b/arch/arm64/kernel/kgdb.c
@@ -0,0 +1,336 @@
+/*
+ * AArch64 KGDB support
+ *
+ * Based on arch/arm/kernel/kgdb.c
+ *
+ * Copyright (C) 2013 Cavium Inc.
+ * Author: Vijaya Kumar K <vijaya.kumar@caviumnetworks.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/irq.h>
+#include <linux/kdebug.h>
+#include <linux/kgdb.h>
+#include <asm/traps.h>
+
+struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = {
+        { "x0", 8, offsetof(struct pt_regs, regs[0])},
+        { "x1", 8, offsetof(struct pt_regs, regs[1])},
+        { "x2", 8, offsetof(struct pt_regs, regs[2])},
+        { "x3", 8, offsetof(struct pt_regs, regs[3])},
+        { "x4", 8, offsetof(struct pt_regs, regs[4])},
+        { "x5", 8, offsetof(struct pt_regs, regs[5])},
+        { "x6", 8, offsetof(struct pt_regs, regs[6])},
+        { "x7", 8, offsetof(struct pt_regs, regs[7])},
+        { "x8", 8, offsetof(struct pt_regs, regs[8])},
+        { "x9", 8, offsetof(struct pt_regs, regs[9])},
+        { "x10", 8, offsetof(struct pt_regs, regs[10])},
+        { "x11", 8, offsetof(struct pt_regs, regs[11])},
+        { "x12", 8, offsetof(struct pt_regs, regs[12])},
+        { "x13", 8, offsetof(struct pt_regs, regs[13])},
+        { "x14", 8, offsetof(struct pt_regs, regs[14])},
+        { "x15", 8, offsetof(struct pt_regs, regs[15])},
+        { "x16", 8, offsetof(struct pt_regs, regs[16])},
+        { "x17", 8, offsetof(struct pt_regs, regs[17])},
+        { "x18", 8, offsetof(struct pt_regs, regs[18])},
+        { "x19", 8, offsetof(struct pt_regs, regs[19])},
+        { "x20", 8, offsetof(struct pt_regs, regs[20])},
+        { "x21", 8, offsetof(struct pt_regs, regs[21])},
+        { "x22", 8, offsetof(struct pt_regs, regs[22])},
+        { "x23", 8, offsetof(struct pt_regs, regs[23])},
+        { "x24", 8, offsetof(struct pt_regs, regs[24])},
+        { "x25", 8, offsetof(struct pt_regs, regs[25])},
+        { "x26", 8, offsetof(struct pt_regs, regs[26])},
+        { "x27", 8, offsetof(struct pt_regs, regs[27])},
+        { "x28", 8, offsetof(struct pt_regs, regs[28])},
+        { "x29", 8, offsetof(struct pt_regs, regs[29])},
+        { "x30", 8, offsetof(struct pt_regs, regs[30])},
+        { "sp", 8, offsetof(struct pt_regs, sp)},
+        { "pc", 8, offsetof(struct pt_regs, pc)},
+        { "pstate", 8, offsetof(struct pt_regs, pstate)},
+        { "v0", 16, -1 },
+        { "v1", 16, -1 },
+        { "v2", 16, -1 },
+        { "v3", 16, -1 },
+        { "v4", 16, -1 },
+        { "v5", 16, -1 },
+        { "v6", 16, -1 },
+        { "v7", 16, -1 },
+        { "v8", 16, -1 },
+        { "v9", 16, -1 },
+        { "v10", 16, -1 },
+        { "v11", 16, -1 },
+        { "v12", 16, -1 },
+        { "v13", 16, -1 },
+        { "v14", 16, -1 },
+        { "v15", 16, -1 },
+        { "v16", 16, -1 },
+        { "v17", 16, -1 },
+        { "v18", 16, -1 },
+        { "v19", 16, -1 },
+        { "v20", 16, -1 },
+        { "v21", 16, -1 },
+        { "v22", 16, -1 },
+        { "v23", 16, -1 },
+        { "v24", 16, -1 },
+        { "v25", 16, -1 },
+        { "v26", 16, -1 },
+        { "v27", 16, -1 },
+        { "v28", 16, -1 },
+        { "v29", 16, -1 },
+        { "v30", 16, -1 },
+        { "v31", 16, -1 },
+        { "fpsr", 4, -1 },
+        { "fpcr", 4, -1 },
+};
+
+char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs)
+{
+        if (regno >= DBG_MAX_REG_NUM || regno < 0)
+                return NULL;
+
+        if (dbg_reg_def[regno].offset != -1)
+                memcpy(mem, (void *)regs + dbg_reg_def[regno].offset,
+                       dbg_reg_def[regno].size);
+        else
+                memset(mem, 0, dbg_reg_def[regno].size);
+        return dbg_reg_def[regno].name;
+}
+
+int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
+{
+        if (regno >= DBG_MAX_REG_NUM || regno < 0)
+                return -EINVAL;
+
+        if (dbg_reg_def[regno].offset != -1)
+                memcpy((void *)regs + dbg_reg_def[regno].offset, mem,
+                       dbg_reg_def[regno].size);
+        return 0;
+}
+
+void
+sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
+{
+        struct pt_regs *thread_regs;
+
+        /* Initialize to zero */
+        memset((char *)gdb_regs, 0, NUMREGBYTES);
+        thread_regs = task_pt_regs(task);
+        memcpy((void *)gdb_regs, (void *)thread_regs->regs, GP_REG_BYTES);
+}
+
+void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
+{
+        regs->pc = pc;
+}
+
+static int compiled_break;
+
+static void kgdb_arch_update_addr(struct pt_regs *regs,
+                                char *remcom_in_buffer)
+{
+        unsigned long addr;
+        char *ptr;
+
+        ptr = &remcom_in_buffer[1];
+        if (kgdb_hex2long(&ptr, &addr))
+                kgdb_arch_set_pc(regs, addr);
+        else if (compiled_break == 1)
+                kgdb_arch_set_pc(regs, regs->pc + 4);
+
+        compiled_break = 0;
+}
+
+int kgdb_arch_handle_exception(int exception_vector, int signo,
+                               int err_code, char *remcom_in_buffer,
+                               char *remcom_out_buffer,
+                               struct pt_regs *linux_regs)
+{
+        int err;
+
+        switch (remcom_in_buffer[0]) {
+        case 'D':
+        case 'k':
+                /*
+                 * Packet D (Detach), k (kill). No special handling
+                 * is required here. Handle same as c packet.
+                 */
+        case 'c':
+                /*
+                 * Packet c (Continue) to continue executing.
+                 * Set pc to required address.
+                 * Try to read optional parameter and set pc.
+                 * If this was a compiled breakpoint, we need to move
+                 * to the next instruction else we will just breakpoint
+                 * over and over again.
+                 */
+                kgdb_arch_update_addr(linux_regs, remcom_in_buffer);
+                atomic_set(&kgdb_cpu_doing_single_step, -1);
+                kgdb_single_step =  0;
+
+                /*
+                 * Received continue command, disable single step
+                 */
+                if (kernel_active_single_step())
+                        kernel_disable_single_step();
+
+                err = 0;
+                break;
+        case 's':
+                /*
+                 * Update step address value with address passed
+                 * with step packet.
+                 * On debug exception return PC is copied to ELR
+                 * So just update PC.
+                 * If no step address is passed, resume from the address
+                 * pointed by PC. Do not update PC
+                 */
+                kgdb_arch_update_addr(linux_regs, remcom_in_buffer);
+                atomic_set(&kgdb_cpu_doing_single_step, raw_smp_processor_id());
+                kgdb_single_step =  1;
+
+                /*
+                 * Enable single step handling
+                 */
+                if (!kernel_active_single_step())
+                        kernel_enable_single_step(linux_regs);
+                err = 0;
+                break;
+        default:
+                err = -1;
+        }
+        return err;
+}
+
+static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+        kgdb_handle_exception(1, SIGTRAP, 0, regs);
+        return 0;
+}
+
+static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+        compiled_break = 1;
+        kgdb_handle_exception(1, SIGTRAP, 0, regs);
+
+        return 0;
+}
+
+static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
+{
+        kgdb_handle_exception(1, SIGTRAP, 0, regs);
+        return 0;
+}
+
+static struct break_hook kgdb_brkpt_hook = {
+        .esr_mask       = 0xffffffff,
+        .esr_val        = DBG_ESR_VAL_BRK(KGDB_DYN_DGB_BRK_IMM),
+        .fn             = kgdb_brk_fn
+};
+
+static struct break_hook kgdb_compiled_brkpt_hook = {
+        .esr_mask       = 0xffffffff,
+        .esr_val        = DBG_ESR_VAL_BRK(KDBG_COMPILED_DBG_BRK_IMM),
+        .fn             = kgdb_compiled_brk_fn
+};
+
+static struct step_hook kgdb_step_hook = {
+        .fn             = kgdb_step_brk_fn
+};
+
+static void kgdb_call_nmi_hook(void *ignored)
+{
+        kgdb_nmicallback(raw_smp_processor_id(), get_irq_regs());
+}
+
+void kgdb_roundup_cpus(unsigned long flags)
+{
+        local_irq_enable();
+        smp_call_function(kgdb_call_nmi_hook, NULL, 0);
+        local_irq_disable();
+}
+
+static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+{
+        struct pt_regs *regs = args->regs;
+
+        if (kgdb_handle_exception(1, args->signr, cmd, regs))
+                return NOTIFY_DONE;
+        return NOTIFY_STOP;
+}
+
+static int
+kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
+{
+        unsigned long flags;
+        int ret;
+
+        local_irq_save(flags);
+        ret = __kgdb_notify(ptr, cmd);
+        local_irq_restore(flags);
+
+        return ret;
+}
+
+static struct notifier_block kgdb_notifier = {
+        .notifier_call  = kgdb_notify,
+        /*
+         * Want to be lowest priority
+         */
+        .priority       = -INT_MAX,
+};
+
+/*
+ * kgdb_arch_init - Perform any architecture specific initalization.
+ * This function will handle the initalization of any architecture
+ * specific callbacks.
+ */
+int kgdb_arch_init(void)
+{
+        int ret = register_die_notifier(&kgdb_notifier);
+
+        if (ret != 0)
+                return ret;
+
+        register_break_hook(&kgdb_brkpt_hook);
+        register_break_hook(&kgdb_compiled_brkpt_hook);
+        register_step_hook(&kgdb_step_hook);
+        return 0;
+}
+
+/*
+ * kgdb_arch_exit - Perform any architecture specific uninitalization.
+ * This function will handle the uninitalization of any architecture
+ * specific callbacks, for dynamic registration and unregistration.
+ */
+void kgdb_arch_exit(void)
+{
+        unregister_break_hook(&kgdb_brkpt_hook);
+        unregister_break_hook(&kgdb_compiled_brkpt_hook);
+        unregister_step_hook(&kgdb_step_hook);
+        unregister_die_notifier(&kgdb_notifier);
+}
+
+/*
+ * ARM instructions are always in LE.
+ * Break instruction is encoded in LE format
+ */
+struct kgdb_arch arch_kgdb_ops = {
+        .gdb_bpt_instr = {
+                KGDB_DYN_BRK_INS_BYTE0,
+                KGDB_DYN_BRK_INS_BYTE1,
+                KGDB_DYN_BRK_INS_BYTE2,
+                KGDB_DYN_BRK_INS_BYTE3,
+        }
+};
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 5b1cd792274a..e868c72a7938 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1348,8 +1348,8 @@ early_initcall(init_hw_perf_events);
  * Callchain handling code.
  */
 struct frame_tail {
-        struct frame_tail   __user *fp;
-        unsigned long       lr;
+        struct frame_tail       __user *fp;
+        unsigned long           lr;
 } __attribute__((packed));
 
 /*
@@ -1386,22 +1386,80 @@ user_backtrace(struct frame_tail __user *tail,
         return buftail.fp;
 }
 
+/*
+ * The registers we're interested in are at the end of the variable
+ * length saved register structure. The fp points at the end of this
+ * structure so the address of this struct is:
+ * (struct compat_frame_tail *)(xxx->fp)-1
+ *
+ * This code has been adapted from the ARM OProfile support.
+ */
+struct compat_frame_tail {
+        compat_uptr_t   fp; /* a (struct compat_frame_tail *) in compat mode */
+        u32             sp;
+        u32             lr;
+} __attribute__((packed));
+
+static struct compat_frame_tail __user *
+compat_user_backtrace(struct compat_frame_tail __user *tail,
+                      struct perf_callchain_entry *entry)
+{
+        struct compat_frame_tail buftail;
+        unsigned long err;
+
+        /* Also check accessibility of one struct frame_tail beyond */
+        if (!access_ok(VERIFY_READ, tail, sizeof(buftail)))
+                return NULL;
+
+        pagefault_disable();
+        err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail));
+        pagefault_enable();
+
+        if (err)
+                return NULL;
+
+        perf_callchain_store(entry, buftail.lr);
+
+        /*
+         * Frame pointers should strictly progress back up the stack
+         * (towards higher addresses).
+         */
+        if (tail + 1 >= (struct compat_frame_tail __user *)
+                        compat_ptr(buftail.fp))
+                return NULL;
+
+        return (struct compat_frame_tail __user *)compat_ptr(buftail.fp) - 1;
+}
+
 void perf_callchain_user(struct perf_callchain_entry *entry,
                          struct pt_regs *regs)
 {
-        struct frame_tail __user *tail;
-
         if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
                 /* We don't support guest os callchain now */
                 return;
         }
 
         perf_callchain_store(entry, regs->pc);
-        tail = (struct frame_tail __user *)regs->regs[29];
 
-        while (entry->nr < PERF_MAX_STACK_DEPTH &&
-               tail && !((unsigned long)tail & 0xf))
-                tail = user_backtrace(tail, entry);
+        if (!compat_user_mode(regs)) {
+                /* AARCH64 mode */
+                struct frame_tail __user *tail;
+
+                tail = (struct frame_tail __user *)regs->regs[29];
+
+                while (entry->nr < PERF_MAX_STACK_DEPTH &&
+                       tail && !((unsigned long)tail & 0xf))
+                        tail = user_backtrace(tail, entry);
+        } else {
+                /* AARCH32 compat mode */
+                struct compat_frame_tail __user *tail;
+
+                tail = (struct compat_frame_tail __user *)regs->compat_fp - 1;
+
+                while ((entry->nr < PERF_MAX_STACK_DEPTH) &&
+                        tail && !((unsigned long)tail & 0x3))
+                        tail = compat_user_backtrace(tail, entry);
+        }
 }
 
 /*
@@ -1429,6 +1487,7 @@ void perf_callchain_kernel(struct perf_callchain_entry *entry,
         frame.fp = regs->regs[29];
         frame.sp = regs->sp;
         frame.pc = regs->pc;
+
         walk_stackframe(&frame, callchain_trace, entry);
 }
 
diff --git a/arch/arm64/kernel/perf_regs.c b/arch/arm64/kernel/perf_regs.c
new file mode 100644
index 000000000000..f2d6f0a36d63
--- /dev/null
+++ b/arch/arm64/kernel/perf_regs.c
@@ -0,0 +1,44 @@
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+        if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_MAX))
+                return 0;
+
+        /*
+         * Compat (i.e. 32 bit) mode:
+         * - PC has been set in the pt_regs struct in kernel_entry,
+         * - Handle SP and LR here.
+         */
+        if (compat_user_mode(regs)) {
+                if ((u32)idx == PERF_REG_ARM64_SP)
+                        return regs->compat_sp;
+                if ((u32)idx == PERF_REG_ARM64_LR)
+                        return regs->compat_lr;
+        }
+
+        return regs->regs[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_ARM64_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+        if (!mask || mask & REG_RESERVED)
+                return -EINVAL;
+
+        return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+        if (is_compat_thread(task_thread_info(task)))
+                return PERF_SAMPLE_REGS_ABI_32;
+        else
+                return PERF_SAMPLE_REGS_ABI_64;
+}
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 1c0a9be2ffa8..6391485f342d 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -33,7 +33,6 @@
 #include <linux/kallsyms.h>
 #include <linux/init.h>
 #include <linux/cpu.h>
-#include <linux/cpuidle.h>
 #include <linux/elfcore.h>
 #include <linux/pm.h>
 #include <linux/tick.h>
@@ -72,8 +71,17 @@ static void setup_restart(void)
 
 void soft_restart(unsigned long addr)
 {
+        typedef void (*phys_reset_t)(unsigned long);
+        phys_reset_t phys_reset;
+
         setup_restart();
-        cpu_reset(addr);
+
+        /* Switch to the identity mapping */
+        phys_reset = (phys_reset_t)virt_to_phys(cpu_reset);
+        phys_reset(addr);
+
+        /* Should never get here */
+        BUG();
 }
 
 /*
@@ -94,10 +102,8 @@ void arch_cpu_idle(void)
          * This should do all the clock switching and wait for interrupt
          * tricks
          */
-        if (cpuidle_idle_call()) {
-                cpu_do_idle();
-                local_irq_enable();
-        }
+        cpu_do_idle();
+        local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/arm64/kernel/psci.c b/arch/arm64/kernel/psci.c
index 4f97db3d7363..ea4828a4aa96 100644
--- a/arch/arm64/kernel/psci.c
+++ b/arch/arm64/kernel/psci.c
@@ -176,22 +176,20 @@ static const struct of_device_id psci_of_match[] __initconst = {
         {},
 };
 
-int __init psci_init(void)
+void __init psci_init(void)
 {
         struct device_node *np;
         const char *method;
         u32 id;
-        int err = 0;
 
         np = of_find_matching_node(NULL, psci_of_match);
         if (!np)
-                return -ENODEV;
+                return;
 
         pr_info("probing function IDs from device-tree\n");
 
         if (of_property_read_string(np, "method", &method)) {
                 pr_warning("missing \"method\" property\n");
-                err = -ENXIO;
                 goto out_put_node;
         }
 
@@ -201,7 +199,6 @@ int __init psci_init(void)
                 invoke_psci_fn = __invoke_psci_fn_smc;
         } else {
                 pr_warning("invalid \"method\" property: %s\n", method);
-                err = -EINVAL;
                 goto out_put_node;
         }
 
@@ -227,7 +224,7 @@ int __init psci_init(void)
 
 out_put_node:
         of_node_put(np);
-        return err;
+        return;
 }
 
 #ifdef CONFIG_SMP
@@ -251,7 +248,7 @@ static int cpu_psci_cpu_boot(unsigned int cpu)
 {
         int err = psci_ops.cpu_on(cpu_logical_map(cpu), __pa(secondary_entry));
         if (err)
-                pr_err("psci: failed to boot CPU%d (%d)\n", cpu, err);
+                pr_err("failed to boot CPU%d (%d)\n", cpu, err);
 
         return err;
 }
@@ -278,7 +275,7 @@ static void cpu_psci_cpu_die(unsigned int cpu)
 
         ret = psci_ops.cpu_off(state);
 
-        pr_crit("psci: unable to power off CPU%u (%d)\n", cpu, ret);
+        pr_crit("unable to power off CPU%u (%d)\n", cpu, ret);
 }
 #endif
 
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index c8e9effe52e1..67da30741a1b 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -69,6 +69,7 @@ EXPORT_SYMBOL_GPL(elf_hwcap);
                                  COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\
                                  COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV)
 unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT;
+unsigned int compat_elf_hwcap2 __read_mostly;
 #endif
 
 static const char *cpu_name;
@@ -242,6 +243,38 @@ static void __init setup_processor(void)
         block = (features >> 16) & 0xf;
         if (block && !(block & 0x8))
                 elf_hwcap |= HWCAP_CRC32;
+
+#ifdef CONFIG_COMPAT
+        /*
+         * ID_ISAR5_EL1 carries similar information as above, but pertaining to
+         * the Aarch32 32-bit execution state.
+         */
+        features = read_cpuid(ID_ISAR5_EL1);
+        block = (features >> 4) & 0xf;
+        if (!(block & 0x8)) {
+                switch (block) {
+                default:
+                case 2:
+                        compat_elf_hwcap2 |= COMPAT_HWCAP2_PMULL;
+                case 1:
+                        compat_elf_hwcap2 |= COMPAT_HWCAP2_AES;
+                case 0:
+                        break;
+                }
+        }
+
+        block = (features >> 8) & 0xf;
+        if (block && !(block & 0x8))
+                compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA1;
+
+        block = (features >> 12) & 0xf;
+        if (block && !(block & 0x8))
+                compat_elf_hwcap2 |= COMPAT_HWCAP2_SHA2;
+
+        block = (features >> 16) & 0xf;
+        if (block && !(block & 0x8))
+                compat_elf_hwcap2 |= COMPAT_HWCAP2_CRC32;
+#endif
 }
 
 static void __init setup_machine_fdt(phys_addr_t dt_phys)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 7cfb92a4ab66..f0a141dd5655 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -114,6 +114,11 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
         return ret;
 }
 
+static void smp_store_cpu_info(unsigned int cpuid)
+{
+        store_cpu_topology(cpuid);
+}
+
 /*
  * This is the secondary CPU boot entry.  We're using this CPUs
  * idle thread stack, but a set of temporary page tables.
@@ -152,6 +157,8 @@ asmlinkage void secondary_start_kernel(void)
          */
         notify_cpu_starting(cpu);
 
+        smp_store_cpu_info(cpu);
+
         /*
          * OK, now it's safe to let the boot CPU continue.  Wait for
          * the CPU migration code to notice that the CPU is online
@@ -160,6 +167,7 @@ asmlinkage void secondary_start_kernel(void)
         set_cpu_online(cpu, true);
         complete(&cpu_running);
 
+        local_dbg_enable();
         local_irq_enable();
         local_async_enable();
 
@@ -390,6 +398,10 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
         int err;
         unsigned int cpu, ncores = num_possible_cpus();
 
+        init_cpu_topology();
+
+        smp_store_cpu_info(smp_processor_id());
+
         /*
          * are we trying to boot more cores than exist?
          */
diff --git a/arch/arm64/kernel/smp_spin_table.c b/arch/arm64/kernel/smp_spin_table.c
index 44c22805d2e2..7a530d2cc807 100644
--- a/arch/arm64/kernel/smp_spin_table.c
+++ b/arch/arm64/kernel/smp_spin_table.c
@@ -128,7 +128,7 @@ static int smp_spin_table_cpu_boot(unsigned int cpu)
         return secondary_holding_pen_release != INVALID_HWID ? -ENOSYS : 0;
 }
 
-void smp_spin_table_cpu_postboot(void)
+static void smp_spin_table_cpu_postboot(void)
 {
         /*
          * Let the primary processor know we're out of the pen.
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index c3b6c63ea5fb..38f0558f0c0a 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -48,7 +48,11 @@ int unwind_frame(struct stackframe *frame)
 
         frame->sp = fp + 0x10;
         frame->fp = *(unsigned long *)(fp);
-        frame->pc = *(unsigned long *)(fp + 8);
+        /*
+         * -4 here because we care about the PC at time of bl,
+         * not where the return will go.
+         */
+        frame->pc = *(unsigned long *)(fp + 8) - 4;
 
         return 0;
 }
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
new file mode 100644
index 000000000000..3e06b0be4ec8
--- /dev/null
+++ b/arch/arm64/kernel/topology.c
@@ -0,0 +1,95 @@
+/*
+ * arch/arm64/kernel/topology.c
+ *
+ * Copyright (C) 2011,2013,2014 Linaro Limited.
+ *
+ * Based on the arm32 version written by Vincent Guittot in turn based on
+ * arch/sh/kernel/topology.c
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <linux/percpu.h>
+#include <linux/node.h>
+#include <linux/nodemask.h>
+#include <linux/sched.h>
+
+#include <asm/topology.h>
+
+/*
+ * cpu topology table
+ */
+struct cpu_topology cpu_topology[NR_CPUS];
+EXPORT_SYMBOL_GPL(cpu_topology);
+
+const struct cpumask *cpu_coregroup_mask(int cpu)
+{
+        return &cpu_topology[cpu].core_sibling;
+}
+
+static void update_siblings_masks(unsigned int cpuid)
+{
+        struct cpu_topology *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+        int cpu;
+
+        if (cpuid_topo->cluster_id == -1) {
+                /*
+                 * DT does not contain topology information for this cpu
+                 * reset it to default behaviour
+                 */
+                pr_debug("CPU%u: No topology information configured\n", cpuid);
+                cpuid_topo->core_id = 0;
+                cpumask_set_cpu(cpuid, &cpuid_topo->core_sibling);
+                cpumask_set_cpu(cpuid, &cpuid_topo->thread_sibling);
+                return;
+        }
+
+        /* update core and thread sibling masks */
+        for_each_possible_cpu(cpu) {
+                cpu_topo = &cpu_topology[cpu];
+
+                if (cpuid_topo->cluster_id != cpu_topo->cluster_id)
+                        continue;
+
+                cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+                if (cpu != cpuid)
+                        cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+                if (cpuid_topo->core_id != cpu_topo->core_id)
+                        continue;
+
+                cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+                if (cpu != cpuid)
+                        cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+        }
+}
+
+void store_cpu_topology(unsigned int cpuid)
+{
+        update_siblings_masks(cpuid);
+}
+
+/*
+ * init_cpu_topology is called at boot when only one cpu is running
+ * which prevent simultaneous write access to cpu_topology array
+ */
+void __init init_cpu_topology(void)
+{
+        unsigned int cpu;
+
+        /* init core mask and power*/
+        for_each_possible_cpu(cpu) {
+                struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+                cpu_topo->thread_id = -1;
+                cpu_topo->core_id =  -1;
+                cpu_topo->cluster_id = -1;
+                cpumask_clear(&cpu_topo->core_sibling);
+                cpumask_clear(&cpu_topo->thread_sibling);
+        }
+}
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index a7149cae1615..50384fec56c4 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -106,49 +106,31 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
 
 static int __init vdso_init(void)
 {
-        struct page *pg;
-        char *vbase;
-        int i, ret = 0;
+        int i;
+
+        if (memcmp(&vdso_start, "\177ELF", 4)) {
+                pr_err("vDSO is not a valid ELF object!\n");
+                return -EINVAL;
+        }
 
         vdso_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
         pr_info("vdso: %ld pages (%ld code, %ld data) at base %p\n",
                 vdso_pages + 1, vdso_pages, 1L, &vdso_start);
 
         /* Allocate the vDSO pagelist, plus a page for the data. */
-        vdso_pagelist = kzalloc(sizeof(struct page *) * (vdso_pages + 1),
+        vdso_pagelist = kcalloc(vdso_pages + 1, sizeof(struct page *),
                                 GFP_KERNEL);
-        if (vdso_pagelist == NULL) {
-                pr_err("Failed to allocate vDSO pagelist!\n");
+        if (vdso_pagelist == NULL)
                 return -ENOMEM;
-        }
 
         /* Grab the vDSO code pages. */
-        for (i = 0; i < vdso_pages; i++) {
-                pg = virt_to_page(&vdso_start + i*PAGE_SIZE);
-                ClearPageReserved(pg);
-                get_page(pg);
-                vdso_pagelist[i] = pg;
-        }
-
-        /* Sanity check the shared object header. */
-        vbase = vmap(vdso_pagelist, 1, 0, PAGE_KERNEL);
-        if (vbase == NULL) {
-                pr_err("Failed to map vDSO pagelist!\n");
-                return -ENOMEM;
-        } else if (memcmp(vbase, "\177ELF", 4)) {
-                pr_err("vDSO is not a valid ELF object!\n");
-                ret = -EINVAL;
-                goto unmap;
-        }
+        for (i = 0; i < vdso_pages; i++)
+                vdso_pagelist[i] = virt_to_page(&vdso_start + i * PAGE_SIZE);
 
         /* Grab the vDSO data page. */
-        pg = virt_to_page(vdso_data);
-        get_page(pg);
-        vdso_pagelist[i] = pg;
+        vdso_pagelist[i] = virt_to_page(vdso_data);
 
-unmap:
-        vunmap(vbase);
-        return ret;
+        return 0;
 }
 arch_initcall(vdso_init);
 
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 2b0244d65c16..d968796f4b2d 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -68,6 +68,12 @@ __do_hyp_init:
         msr     tcr_el2, x4
 
         ldr     x4, =VTCR_EL2_FLAGS
+        /*
+         * Read the PARange bits from ID_AA64MMFR0_EL1 and set the PS bits in
+         * VTCR_EL2.
+         */
+        mrs     x5, ID_AA64MMFR0_EL1
+        bfi     x4, x5, #16, #3
         msr     vtcr_el2, x4
 
         mrs     x4, mair_el1
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 3b47c36e10ff..2c56012cb2d2 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -694,6 +694,24 @@ __hyp_panic_str:
 
         .align  2
 
+/*
+ * u64 kvm_call_hyp(void *hypfn, ...);
+ *
+ * This is not really a variadic function in the classic C-way and care must
+ * be taken when calling this to ensure parameters are passed in registers
+ * only, since the stack will change between the caller and the callee.
+ *
+ * Call the function with the first argument containing a pointer to the
+ * function you wish to call in Hyp mode, and subsequent arguments will be
+ * passed as x0, x1, and x2 (a maximum of 3 arguments in addition to the
+ * function pointer can be passed).  The function being called must be mapped
+ * in Hyp mode (see init_hyp_mode in arch/arm/kvm/arm.c).  Return values are
+ * passed in r0 and r1.
+ *
+ * A function pointer with a value of 0 has a special meaning, and is
+ * used to implement __hyp_get_vectors in the same way as in
+ * arch/arm64/kernel/hyp_stub.S.
+ */
 ENTRY(kvm_call_hyp)
         hvc     #0
         ret
@@ -737,7 +755,12 @@ el1_sync:					// Guest trapped into EL2
         pop     x2, x3
         pop     x0, x1
 
-        push    lr, xzr
+        /* Check for __hyp_get_vectors */
+        cbnz    x0, 1f
+        mrs     x0, vbar_el2
+        b       2f
+
+1:      push    lr, xzr
 
         /*
          * Compute the function address in EL2, and shuffle the parameters.
@@ -750,7 +773,7 @@ el1_sync:					// Guest trapped into EL2
         blr     lr
 
         pop     lr, xzr
-        eret
+2:      eret
 
 el1_trap:
         /*
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 1ea9f26d1b70..c46f48b33c14 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -30,7 +30,7 @@
  *
  *      Corrupted registers: x0-x7, x9-x11
  */
-ENTRY(__flush_dcache_all)
+__flush_dcache_all:
         dsb     sy                              // ensure ordering with previous memory accesses
         mrs     x0, clidr_el1                   // read clidr
         and     x3, x0, #0x7000000              // extract loc from clidr
@@ -166,3 +166,81 @@ ENTRY(__flush_dcache_area)
         dsb     sy
         ret
 ENDPROC(__flush_dcache_area)
+
+/*
+ *      __dma_inv_range(start, end)
+ *      - start   - virtual start address of region
+ *      - end     - virtual end address of region
+ */
+__dma_inv_range:
+        dcache_line_size x2, x3
+        sub     x3, x2, #1
+        bic     x0, x0, x3
+        bic     x1, x1, x3
+1:      dc      ivac, x0                        // invalidate D / U line
+        add     x0, x0, x2
+        cmp     x0, x1
+        b.lo    1b
+        dsb     sy
+        ret
+ENDPROC(__dma_inv_range)
+
+/*
+ *      __dma_clean_range(start, end)
+ *      - start   - virtual start address of region
+ *      - end     - virtual end address of region
+ */
+__dma_clean_range:
+        dcache_line_size x2, x3
+        sub     x3, x2, #1
+        bic     x0, x0, x3
+1:      dc      cvac, x0                        // clean D / U line
+        add     x0, x0, x2
+        cmp     x0, x1
+        b.lo    1b
+        dsb     sy
+        ret
+ENDPROC(__dma_clean_range)
+
+/*
+ *      __dma_flush_range(start, end)
+ *      - start   - virtual start address of region
+ *      - end     - virtual end address of region
+ */
+ENTRY(__dma_flush_range)
+        dcache_line_size x2, x3
+        sub     x3, x2, #1
+        bic     x0, x0, x3
+1:      dc      civac, x0                       // clean & invalidate D / U line
+        add     x0, x0, x2
+        cmp     x0, x1
+        b.lo    1b
+        dsb     sy
+        ret
+ENDPROC(__dma_flush_range)
+
+/*
+ *      __dma_map_area(start, size, dir)
+ *      - start - kernel virtual start address
+ *      - size  - size of region
+ *      - dir   - DMA direction
+ */
+ENTRY(__dma_map_area)
+        add     x1, x1, x0
+        cmp     w2, #DMA_FROM_DEVICE
+        b.eq    __dma_inv_range
+        b       __dma_clean_range
+ENDPROC(__dma_map_area)
+
+/*
+ *      __dma_unmap_area(start, size, dir)
+ *      - start - kernel virtual start address
+ *      - size  - size of region
+ *      - dir   - DMA direction
+ */
+ENTRY(__dma_unmap_area)
+        add     x1, x1, x0
+        cmp     w2, #DMA_TO_DEVICE
+        b.ne    __dma_inv_range
+        ret
+ENDPROC(__dma_unmap_area)
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index fbd76785c5db..0ba347e59f06 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -30,18 +30,26 @@
 struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
-static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
-                                          dma_addr_t *dma_handle, gfp_t flags,
-                                          struct dma_attrs *attrs)
+static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
+                                 bool coherent)
+{
+        if (!coherent || dma_get_attr(DMA_ATTR_WRITE_COMBINE, attrs))
+                return pgprot_writecombine(prot);
+        return prot;
+}
+
+static void *__dma_alloc_coherent(struct device *dev, size_t size,
+                                  dma_addr_t *dma_handle, gfp_t flags,
+                                  struct dma_attrs *attrs)
 {
         if (dev == NULL) {
                 WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
                 return NULL;
         }
 
-        if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+        if (IS_ENABLED(CONFIG_ZONE_DMA) &&
             dev->coherent_dma_mask <= DMA_BIT_MASK(32))
-                flags |= GFP_DMA32;
+                flags |= GFP_DMA;
         if (IS_ENABLED(CONFIG_DMA_CMA)) {
                 struct page *page;
 
@@ -58,9 +66,9 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
         }
 }
 
-static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
-                                        void *vaddr, dma_addr_t dma_handle,
-                                        struct dma_attrs *attrs)
+static void __dma_free_coherent(struct device *dev, size_t size,
+                                void *vaddr, dma_addr_t dma_handle,
+                                struct dma_attrs *attrs)
 {
         if (dev == NULL) {
                 WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
@@ -78,9 +86,212 @@ static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
         }
 }
 
-static struct dma_map_ops arm64_swiotlb_dma_ops = {
-        .alloc = arm64_swiotlb_alloc_coherent,
-        .free = arm64_swiotlb_free_coherent,
+static void *__dma_alloc_noncoherent(struct device *dev, size_t size,
+                                     dma_addr_t *dma_handle, gfp_t flags,
+                                     struct dma_attrs *attrs)
+{
+        struct page *page, **map;
+        void *ptr, *coherent_ptr;
+        int order, i;
+
+        size = PAGE_ALIGN(size);
+        order = get_order(size);
+
+        ptr = __dma_alloc_coherent(dev, size, dma_handle, flags, attrs);
+        if (!ptr)
+                goto no_mem;
+        map = kmalloc(sizeof(struct page *) << order, flags & ~GFP_DMA);
+        if (!map)
+                goto no_map;
+
+        /* remove any dirty cache lines on the kernel alias */
+        __dma_flush_range(ptr, ptr + size);
+
+        /* create a coherent mapping */
+        page = virt_to_page(ptr);
+        for (i = 0; i < (size >> PAGE_SHIFT); i++)
+                map[i] = page + i;
+        coherent_ptr = vmap(map, size >> PAGE_SHIFT, VM_MAP,
+                            __get_dma_pgprot(attrs, pgprot_default, false));
+        kfree(map);
+        if (!coherent_ptr)
+                goto no_map;
+
+        return coherent_ptr;
+
+no_map:
+        __dma_free_coherent(dev, size, ptr, *dma_handle, attrs);
+no_mem:
+        *dma_handle = ~0;
+        return NULL;
+}
+
+static void __dma_free_noncoherent(struct device *dev, size_t size,
+                                   void *vaddr, dma_addr_t dma_handle,
+                                   struct dma_attrs *attrs)
+{
+        void *swiotlb_addr = phys_to_virt(dma_to_phys(dev, dma_handle));
+
+        vunmap(vaddr);
+        __dma_free_coherent(dev, size, swiotlb_addr, dma_handle, attrs);
+}
+
+static dma_addr_t __swiotlb_map_page(struct device *dev, struct page *page,
+                                     unsigned long offset, size_t size,
+                                     enum dma_data_direction dir,
+                                     struct dma_attrs *attrs)
+{
+        dma_addr_t dev_addr;
+
+        dev_addr = swiotlb_map_page(dev, page, offset, size, dir, attrs);
+        __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+
+        return dev_addr;
+}
+
+
+static void __swiotlb_unmap_page(struct device *dev, dma_addr_t dev_addr,
+                                 size_t size, enum dma_data_direction dir,
+                                 struct dma_attrs *attrs)
+{
+        __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+        swiotlb_unmap_page(dev, dev_addr, size, dir, attrs);
+}
+
+static int __swiotlb_map_sg_attrs(struct device *dev, struct scatterlist *sgl,
+                                  int nelems, enum dma_data_direction dir,
+                                  struct dma_attrs *attrs)
+{
+        struct scatterlist *sg;
+        int i, ret;
+
+        ret = swiotlb_map_sg_attrs(dev, sgl, nelems, dir, attrs);
+        for_each_sg(sgl, sg, ret, i)
+                __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+                               sg->length, dir);
+
+        return ret;
+}
+
+static void __swiotlb_unmap_sg_attrs(struct device *dev,
+                                     struct scatterlist *sgl, int nelems,
+                                     enum dma_data_direction dir,
+                                     struct dma_attrs *attrs)
+{
+        struct scatterlist *sg;
+        int i;
+
+        for_each_sg(sgl, sg, nelems, i)
+                __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+                                 sg->length, dir);
+        swiotlb_unmap_sg_attrs(dev, sgl, nelems, dir, attrs);
+}
+
+static void __swiotlb_sync_single_for_cpu(struct device *dev,
+                                          dma_addr_t dev_addr, size_t size,
+                                          enum dma_data_direction dir)
+{
+        __dma_unmap_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+        swiotlb_sync_single_for_cpu(dev, dev_addr, size, dir);
+}
+
+static void __swiotlb_sync_single_for_device(struct device *dev,
+                                             dma_addr_t dev_addr, size_t size,
+                                             enum dma_data_direction dir)
+{
+        swiotlb_sync_single_for_device(dev, dev_addr, size, dir);
+        __dma_map_area(phys_to_virt(dma_to_phys(dev, dev_addr)), size, dir);
+}
+
+static void __swiotlb_sync_sg_for_cpu(struct device *dev,
+                                      struct scatterlist *sgl, int nelems,
+                                      enum dma_data_direction dir)
+{
+        struct scatterlist *sg;
+        int i;
+
+        for_each_sg(sgl, sg, nelems, i)
+                __dma_unmap_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+                                 sg->length, dir);
+        swiotlb_sync_sg_for_cpu(dev, sgl, nelems, dir);
+}
+
+static void __swiotlb_sync_sg_for_device(struct device *dev,
+                                         struct scatterlist *sgl, int nelems,
+                                         enum dma_data_direction dir)
+{
+        struct scatterlist *sg;
+        int i;
+
+        swiotlb_sync_sg_for_device(dev, sgl, nelems, dir);
+        for_each_sg(sgl, sg, nelems, i)
+                __dma_map_area(phys_to_virt(dma_to_phys(dev, sg->dma_address)),
+                               sg->length, dir);
+}
+
+/* vma->vm_page_prot must be set appropriately before calling this function */
+static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+                             void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+        int ret = -ENXIO;
+        unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >>
+                                        PAGE_SHIFT;
+        unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+        unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT;
+        unsigned long off = vma->vm_pgoff;
+
+        if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
+                return ret;
+
+        if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+                ret = remap_pfn_range(vma, vma->vm_start,
+                                      pfn + off,
+                                      vma->vm_end - vma->vm_start,
+                                      vma->vm_page_prot);
+        }
+
+        return ret;
+}
+
+static int __swiotlb_mmap_noncoherent(struct device *dev,
+                struct vm_area_struct *vma,
+                void *cpu_addr, dma_addr_t dma_addr, size_t size,
+                struct dma_attrs *attrs)
+{
+        vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, false);
+        return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+static int __swiotlb_mmap_coherent(struct device *dev,
+                struct vm_area_struct *vma,
+                void *cpu_addr, dma_addr_t dma_addr, size_t size,
+                struct dma_attrs *attrs)
+{
+        /* Just use whatever page_prot attributes were specified */
+        return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+
+struct dma_map_ops noncoherent_swiotlb_dma_ops = {
+        .alloc = __dma_alloc_noncoherent,
+        .free = __dma_free_noncoherent,
+        .mmap = __swiotlb_mmap_noncoherent,
+        .map_page = __swiotlb_map_page,
+        .unmap_page = __swiotlb_unmap_page,
+        .map_sg = __swiotlb_map_sg_attrs,
+        .unmap_sg = __swiotlb_unmap_sg_attrs,
+        .sync_single_for_cpu = __swiotlb_sync_single_for_cpu,
+        .sync_single_for_device = __swiotlb_sync_single_for_device,
+        .sync_sg_for_cpu = __swiotlb_sync_sg_for_cpu,
+        .sync_sg_for_device = __swiotlb_sync_sg_for_device,
+        .dma_supported = swiotlb_dma_supported,
+        .mapping_error = swiotlb_dma_mapping_error,
+};
+EXPORT_SYMBOL(noncoherent_swiotlb_dma_ops);
+
+struct dma_map_ops coherent_swiotlb_dma_ops = {
+        .alloc = __dma_alloc_coherent,
+        .free = __dma_free_coherent,
+        .mmap = __swiotlb_mmap_coherent,
         .map_page = swiotlb_map_page,
         .unmap_page = swiotlb_unmap_page,
         .map_sg = swiotlb_map_sg_attrs,
@@ -92,12 +303,19 @@ static struct dma_map_ops arm64_swiotlb_dma_ops = {
         .dma_supported = swiotlb_dma_supported,
         .mapping_error = swiotlb_dma_mapping_error,
 };
+EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
+
+extern int swiotlb_late_init_with_default_size(size_t default_size);
 
-void __init arm64_swiotlb_init(void)
+static int __init swiotlb_late_init(void)
 {
-        dma_ops = &arm64_swiotlb_dma_ops;
-        swiotlb_init(1);
+        size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
+
+        dma_ops = &coherent_swiotlb_dma_ops;
+
+        return swiotlb_late_init_with_default_size(swiotlb_size);
 }
+subsys_initcall(swiotlb_late_init);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES      4096
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index d0b4c2efda90..88627c450a6c 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 
 #include <asm/sections.h>
@@ -59,22 +60,22 @@ static int __init early_initrd(char *p)
 early_param("initrd", early_initrd);
 #endif
 
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
-
 static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
         struct memblock_region *reg;
         unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-        unsigned long max_dma32 = min;
+        unsigned long max_dma = min;
 
         memset(zone_size, 0, sizeof(zone_size));
 
-#ifdef CONFIG_ZONE_DMA32
         /* 4GB maximum for 32-bit only capable devices */
-        max_dma32 = max(min, min(max, MAX_DMA32_PFN));
-        zone_size[ZONE_DMA32] = max_dma32 - min;
-#endif
-        zone_size[ZONE_NORMAL] = max - max_dma32;
+        if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+                unsigned long max_dma_phys =
+                        (unsigned long)dma_to_phys(NULL, DMA_BIT_MASK(32) + 1);
+                max_dma = max(min, min(max, max_dma_phys >> PAGE_SHIFT));
+                zone_size[ZONE_DMA] = max_dma - min;
+        }
+        zone_size[ZONE_NORMAL] = max - max_dma;
 
         memcpy(zhole_size, zone_size, sizeof(zhole_size));
 
@@ -84,15 +85,15 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
                 if (start >= max)
                         continue;
-#ifdef CONFIG_ZONE_DMA32
-                if (start < max_dma32) {
-                        unsigned long dma_end = min(end, max_dma32);
-                        zhole_size[ZONE_DMA32] -= dma_end - start;
+
+                if (IS_ENABLED(CONFIG_ZONE_DMA) && start < max_dma) {
+                        unsigned long dma_end = min(end, max_dma);
+                        zhole_size[ZONE_DMA] -= dma_end - start;
                 }
-#endif
-                if (end > max_dma32) {
+
+                if (end > max_dma) {
                         unsigned long normal_end = min(end, max);
-                        unsigned long normal_start = max(start, max_dma32);
+                        unsigned long normal_start = max(start, max_dma);
                         zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
                 }
         }
@@ -261,8 +262,6 @@ static void __init free_unused_memmap(void)
  */
 void __init mem_init(void)
 {
-        arm64_swiotlb_init();
-
         max_mapnr   = pfn_to_page(max_pfn + PHYS_PFN_OFFSET) - mem_map;
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 1333e6f9a8e5..e085ee6ef4e2 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -173,12 +173,6 @@ ENDPROC(cpu_do_switch_mm)
  *      value of the SCTLR_EL1 register.
  */
 ENTRY(__cpu_setup)
-        /*
-         * Preserve the link register across the function call.
-         */
-        mov     x28, lr
-        bl      __flush_dcache_all
-        mov     lr, x28
         ic      iallu                           // I+BTB cache invalidate
         tlbi    vmalle1is                       // invalidate I + D TLBs
         dsb     sy
@@ -215,8 +209,14 @@ ENTRY(__cpu_setup)
          * Set/prepare TCR and TTBR. We use 512GB (39-bit) address range for
          * both user and kernel.
          */
-        ldr     x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | TCR_IPS_40BIT | \
+        ldr     x10, =TCR_TxSZ(VA_BITS) | TCR_FLAGS | \
                       TCR_ASID16 | TCR_TBI0 | (1 << 31)
+        /*
+         * Read the PARange bits from ID_AA64MMFR0_EL1 and set the IPS bits in
+         * TCR_EL1.
+         */
+        mrs     x9, ID_AA64MMFR0_EL1
+        bfi     x10, x9, #32, #3
 #ifdef CONFIG_ARM64_64K_PAGES
         orr     x10, x10, TCR_TG0_64K
         orr     x10, x10, TCR_TG1_64K
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index c7c64a63c29f..00a0f3ccd6eb 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -1,22 +1,23 @@
 
-generic-y       += clkdev.h
-generic-y       += cputime.h
-generic-y       += delay.h
-generic-y       += device.h
-generic-y       += div64.h
-generic-y       += emergency-restart.h
-generic-y       += exec.h
-generic-y       += futex.h
-generic-y       += preempt.h
-generic-y       += irq_regs.h
-generic-y       += param.h
-generic-y       += local.h
-generic-y       += local64.h
-generic-y       += percpu.h
-generic-y       += scatterlist.h
-generic-y       += sections.h
-generic-y       += topology.h
-generic-y       += trace_clock.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += delay.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += exec.h
+generic-y += futex.h
+generic-y += hash.h
+generic-y += irq_regs.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += param.h
+generic-y += percpu.h
+generic-y += preempt.h
+generic-y += scatterlist.h
+generic-y += sections.h
+generic-y += topology.h
+generic-y += trace_clock.h
 generic-y += vga.h
-generic-y       += xor.h
-generic-y       += hash.h
+generic-y += xor.h
diff --git a/arch/avr32/include/asm/bugs.h b/arch/avr32/include/asm/bugs.h
index 7635e770622e..278661bbd1b0 100644
--- a/arch/avr32/include/asm/bugs.h
+++ b/arch/avr32/include/asm/bugs.h
@@ -9,7 +9,7 @@
 
 static void __init check_bugs(void)
 {
-        cpu_data->loops_per_jiffy = loops_per_jiffy;
+        boot_cpu_data.loops_per_jiffy = loops_per_jiffy;
 }
 
 #endif /* __ASM_AVR32_BUGS_H */
diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h
index 48d71c5c898a..972adcc1e8f4 100644
--- a/arch/avr32/include/asm/processor.h
+++ b/arch/avr32/include/asm/processor.h
@@ -83,13 +83,8 @@ static inline unsigned int avr32_get_chip_revision(struct avr32_cpuinfo *cpu)
 
 extern struct avr32_cpuinfo boot_cpu_data;
 
-#ifdef CONFIG_SMP
-extern struct avr32_cpuinfo cpu_data[];
-#define current_cpu_data cpu_data[smp_processor_id()]
-#else
-#define cpu_data (&boot_cpu_data)
+/* No SMP support so far */
 #define current_cpu_data boot_cpu_data
-#endif
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's
diff --git a/arch/avr32/kernel/cpu.c b/arch/avr32/kernel/cpu.c
index 2233be71e2e8..0341ae27c9ec 100644
--- a/arch/avr32/kernel/cpu.c
+++ b/arch/avr32/kernel/cpu.c
@@ -39,10 +39,12 @@ static ssize_t store_pc0event(struct device *dev,
                               size_t count)
 {
         unsigned long val;
-        char *endp;
+        int ret;
 
-        val = simple_strtoul(buf, &endp, 0);
-        if (endp == buf || val > 0x3f)
+        ret = kstrtoul(buf, 0, &val);
+        if (ret)
+                return ret;
+        if (val > 0x3f)
                 return -EINVAL;
         val = (val << 12) | (sysreg_read(PCCR) & 0xfffc0fff);
         sysreg_write(PCCR, val);
@@ -61,11 +63,11 @@ static ssize_t store_pc0count(struct device *dev,
                                 const char *buf, size_t count)
 {
         unsigned long val;
-        char *endp;
+        int ret;
 
-        val = simple_strtoul(buf, &endp, 0);
-        if (endp == buf)
-                return -EINVAL;
+        ret = kstrtoul(buf, 0, &val);
+        if (ret)
+                return ret;
         sysreg_write(PCNT0, val);
 
         return count;
@@ -84,10 +86,12 @@ static ssize_t store_pc1event(struct device *dev,
                               size_t count)
 {
         unsigned long val;
-        char *endp;
+        int ret;
 
-        val = simple_strtoul(buf, &endp, 0);
-        if (endp == buf || val > 0x3f)
+        ret = kstrtoul(buf, 0, &val);
+        if (ret)
+                return ret;
+        if (val > 0x3f)
                 return -EINVAL;
         val = (val << 18) | (sysreg_read(PCCR) & 0xff03ffff);
         sysreg_write(PCCR, val);
@@ -106,11 +110,11 @@ static ssize_t store_pc1count(struct device *dev,
                               size_t count)
 {
         unsigned long val;
-        char *endp;
+        int ret;
 
-        val = simple_strtoul(buf, &endp, 0);
-        if (endp == buf)
-                return -EINVAL;
+        ret = kstrtoul(buf, 0, &val);
+        if (ret)
+                return ret;
         sysreg_write(PCNT1, val);
 
         return count;
@@ -129,11 +133,11 @@ static ssize_t store_pccycles(struct device *dev,
                               size_t count)
 {
         unsigned long val;
-        char *endp;
+        int ret;
 
-        val = simple_strtoul(buf, &endp, 0);
-        if (endp == buf)
-                return -EINVAL;
+        ret = kstrtoul(buf, 0, &val);
+        if (ret)
+                return ret;
         sysreg_write(PCCNT, val);
 
         return count;
@@ -152,11 +156,11 @@ static ssize_t store_pcenable(struct device *dev,
                               size_t count)
 {
         unsigned long pccr, val;
-        char *endp;
+        int ret;
 
-        val = simple_strtoul(buf, &endp, 0);
-        if (endp == buf)
-                return -EINVAL;
+        ret = kstrtoul(buf, 0, &val);
+        if (ret)
+                return ret;
         if (val)
                 val = 1;
 
diff --git a/arch/avr32/mm/cache.c b/arch/avr32/mm/cache.c
index 6a46ecd56cfd..85d635cd7b28 100644
--- a/arch/avr32/mm/cache.c
+++ b/arch/avr32/mm/cache.c
@@ -111,6 +111,7 @@ void flush_icache_range(unsigned long start, unsigned long end)
         __flush_icache_range(start & ~(linesz - 1),
                              (end + linesz - 1) & ~(linesz - 1));
 }
+EXPORT_SYMBOL(flush_icache_range);
 
 /*
  * This one is called from __do_fault() and do_swap_page().
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 359d36fdc247..0d93b9a79ca9 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -10,6 +10,7 @@ generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += fb.h
 generic-y += futex.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
@@ -17,14 +18,16 @@ generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += pgalloc.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sembuf.h
@@ -44,5 +47,3 @@ generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += user.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index d73bb85ccdd3..8dbdce8421b0 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -15,6 +15,7 @@ generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += futex.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += io.h
 generic-y += ioctl.h
@@ -24,6 +25,7 @@ generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
+generic-y += mcs_spinlock.h
 generic-y += mman.h
 generic-y += mmu.h
 generic-y += mmu_context.h
@@ -34,6 +36,7 @@ generic-y += percpu.h
 generic-y += pgalloc.h
 generic-y += poll.h
 generic-y += posix_types.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += segment.h
@@ -56,5 +59,3 @@ generic-y += ucontext.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/c6x/include/asm/cache.h b/arch/c6x/include/asm/cache.h
index 09c5a0f5f4d1..86648c083bb4 100644
--- a/arch/c6x/include/asm/cache.h
+++ b/arch/c6x/include/asm/cache.h
@@ -12,6 +12,7 @@
 #define _ASM_C6X_CACHE_H
 
 #include <linux/irqflags.h>
+#include <linux/init.h>
 
 /*
  * Cache line size
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index f3fd8768f095..afff5105909d 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -5,12 +5,14 @@ header-y += arch-v32/
 
 generic-y += barrier.h
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
 generic-y += kvm_para.h
 generic-y += linkage.h
+generic-y += mcs_spinlock.h
 generic-y += module.h
+generic-y += preempt.h
 generic-y += trace_clock.h
 generic-y += vga.h
 generic-y += xor.h
-generic-y += preempt.h
diff --git a/arch/cris/include/asm/bitops.h b/arch/cris/include/asm/bitops.h
index 184066ceb1f6..053c17b36559 100644
--- a/arch/cris/include/asm/bitops.h
+++ b/arch/cris/include/asm/bitops.h
@@ -144,7 +144,7 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
  * definition, which doesn't have the same semantics.  We don't want to
  * use -fno-builtin, so just hide the name ffs.
  */
-#define ffs kernel_ffs
+#define ffs(x) kernel_ffs(x)
 
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
diff --git a/arch/cris/include/asm/cputime.h b/arch/cris/include/asm/cputime.h
deleted file mode 100644
index 4446a65656fa..000000000000
--- a/arch/cris/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __CRIS_CPUTIME_H
-#define __CRIS_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __CRIS_CPUTIME_H */
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index bc42f14c9c2e..87b95eb8aee5 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -1,6 +1,8 @@
 
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += exec.h
-generic-y += trace_clock.h
-generic-y += preempt.h
 generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/frv/include/asm/cputime.h b/arch/frv/include/asm/cputime.h
deleted file mode 100644
index f6c373ad2b80..000000000000
--- a/arch/frv/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_CPUTIME_H
-#define _ASM_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* _ASM_CPUTIME_H */
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 38ca45d3df1e..eadcc118f950 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -25,14 +25,16 @@ generic-y += ipcbuf.h
 generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
-generic-y += local64.h
 generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += pci.h
 generic-y += percpu.h
 generic-y += poll.h
 generic-y += posix_types.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h
 generic-y += scatterlist.h
@@ -45,8 +47,8 @@ generic-y += siginfo.h
 generic-y += sizes.h
 generic-y += socket.h
 generic-y += sockios.h
-generic-y += statfs.h
 generic-y += stat.h
+generic-y += statfs.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
@@ -55,4 +57,3 @@ generic-y += types.h
 generic-y += ucontext.h
 generic-y += unaligned.h
 generic-y += xor.h
-generic-y += preempt.h
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index efbd2929aeb7..6404acbb84b2 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -30,9 +30,9 @@ CONFIG_ACPI_BUTTON=m
 CONFIG_ACPI_FAN=m
 CONFIG_ACPI_DOCK=y
 CONFIG_ACPI_PROCESSOR=m
-CONFIG_ACPI_CONTAINER=m
+CONFIG_ACPI_CONTAINER=y
 CONFIG_HOTPLUG_PCI=y
-CONFIG_HOTPLUG_PCI_ACPI=m
+CONFIG_HOTPLUG_PCI_ACPI=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_INET=y
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
index 8e858b593e4f..30c43d39dede 100644
--- a/arch/ia64/hp/common/sba_iommu.c
+++ b/arch/ia64/hp/common/sba_iommu.c
@@ -1596,7 +1596,7 @@ static void sba_unmap_sg_attrs(struct device *dev, struct scatterlist *sglist,
 *
 ***************************************************************/
 
-static void __init
+static void
 ioc_iova_init(struct ioc *ioc)
 {
         int tcnfg;
@@ -1807,7 +1807,7 @@ static struct ioc_iommu ioc_iommu_info[] __initdata = {
         { SX2000_IOC_ID, "sx2000", NULL },
 };
 
-static struct ioc * __init
+static struct ioc *
 ioc_init(unsigned long hpa, void *handle)
 {
         struct ioc *ioc;
@@ -2041,7 +2041,7 @@ sba_map_ioc_to_node(struct ioc *ioc, acpi_handle handle)
 #define sba_map_ioc_to_node(ioc, handle)
 #endif
 
-static int __init
+static int
 acpi_sba_ioc_add(struct acpi_device *device,
                  const struct acpi_device_id *not_used)
 {
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index 283a83154b5e..0da4aa2602ae 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -1,8 +1,9 @@
 
 generic-y += clkdev.h
 generic-y += exec.h
+generic-y += hash.h
 generic-y += kvm_para.h
-generic-y += trace_clock.h
+generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += trace_clock.h
 generic-y += vtime.h
-generic-y += hash.h
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index a2496e449b75..5cb55a1e606b 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -77,7 +77,6 @@ void build_cpu_to_node_map(void);
 #define topology_core_id(cpu)                   (cpu_data(cpu)->core_id)
 #define topology_core_cpumask(cpu)              (&cpu_core_map[cpu])
 #define topology_thread_cpumask(cpu)            (&per_cpu(cpu_sibling_map, cpu))
-#define smt_capable()                           (smp_num_siblings > 1)
 #endif
 
 extern void arch_fix_phys_package_id(int num, u32 slot);
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index da5b462e6de6..741b99c1a0b1 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -477,6 +477,9 @@ efi_init (void)
         char *cp, vendor[100] = "unknown";
         int i;
 
+        set_bit(EFI_BOOT, &efi.flags);
+        set_bit(EFI_64BIT, &efi.flags);
+
         /*
          * It's too early to be able to use the standard kernel command line
          * support...
@@ -529,6 +532,8 @@ efi_init (void)
                efi.systab->hdr.revision >> 16,
                efi.systab->hdr.revision & 0xffff, vendor);
 
+        set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
         palo_phys      = EFI_INVALID_TABLE_ADDR;
 
         if (efi_config_init(arch_tables) != 0)
@@ -657,6 +662,8 @@ efi_enter_virtual_mode (void)
                 return;
         }
 
+        set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+
         /*
          * Now that EFI is in virtual mode, we call the EFI functions more
          * efficiently:
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 1034884b77da..0884f5ecbcc3 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -364,7 +364,6 @@ static irqreturn_t smp_irq_move_cleanup_interrupt(int irq, void *dev_id)
 
 static struct irqaction irq_move_irqaction = {
         .handler =      smp_irq_move_cleanup_interrupt,
-        .flags =        IRQF_DISABLED,
         .name =         "irq_move"
 };
 
@@ -489,14 +488,13 @@ ia64_handle_irq (ia64_vector vector, struct pt_regs *regs)
         ia64_srlz_d();
         while (vector != IA64_SPURIOUS_INT_VECTOR) {
                 int irq = local_vector_to_irq(vector);
-                struct irq_desc *desc = irq_to_desc(irq);
 
                 if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
                         smp_local_flush_tlb();
-                        kstat_incr_irqs_this_cpu(irq, desc);
+                        kstat_incr_irq_this_cpu(irq);
                 } else if (unlikely(IS_RESCHEDULE(vector))) {
                         scheduler_ipi();
-                        kstat_incr_irqs_this_cpu(irq, desc);
+                        kstat_incr_irq_this_cpu(irq);
                 } else {
                         ia64_setreg(_IA64_REG_CR_TPR, vector);
                         ia64_srlz_d();
@@ -549,13 +547,12 @@ void ia64_process_pending_intr(void)
           */
         while (vector != IA64_SPURIOUS_INT_VECTOR) {
                 int irq = local_vector_to_irq(vector);
-                struct irq_desc *desc = irq_to_desc(irq);
 
                 if (unlikely(IS_LOCAL_TLB_FLUSH(vector))) {
                         smp_local_flush_tlb();
-                        kstat_incr_irqs_this_cpu(irq, desc);
+                        kstat_incr_irq_this_cpu(irq);
                 } else if (unlikely(IS_RESCHEDULE(vector))) {
-                        kstat_incr_irqs_this_cpu(irq, desc);
+                        kstat_incr_irq_this_cpu(irq);
                 } else {
                         struct pt_regs *old_regs = set_irq_regs(NULL);
 
@@ -602,7 +599,6 @@ static irqreturn_t dummy_handler (int irq, void *dev_id)
 
 static struct irqaction ipi_irqaction = {
         .handler =      handle_IPI,
-        .flags =        IRQF_DISABLED,
         .name =         "IPI"
 };
 
@@ -611,13 +607,11 @@ static struct irqaction ipi_irqaction = {
  */
 static struct irqaction resched_irqaction = {
         .handler =      dummy_handler,
-        .flags =        IRQF_DISABLED,
         .name =         "resched"
 };
 
 static struct irqaction tlb_irqaction = {
         .handler =      dummy_handler,
-        .flags =        IRQF_DISABLED,
         .name =         "tlb_flush"
 };
 
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index b8edfa75a83f..db7b36bb068b 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -217,7 +217,7 @@ void ia64_mca_printk(const char *fmt, ...)
         /* Copy the output into mlogbuf */
         if (oops_in_progress) {
                 /* mlogbuf was abandoned, use printk directly instead. */
-                printk(temp_buf);
+                printk("%s", temp_buf);
         } else {
                 spin_lock(&mlogbuf_wlock);
                 for (p = temp_buf; *p; p++) {
@@ -268,7 +268,7 @@ void ia64_mlogbuf_dump(void)
                 }
                 *p = '\0';
                 if (temp_buf[0])
-                        printk(temp_buf);
+                        printk("%s", temp_buf);
                 mlogbuf_start = index;
 
                 mlogbuf_timestamp = 0;
@@ -1772,38 +1772,32 @@ __setup("disable_cpe_poll", ia64_mca_disable_cpe_polling);
 
 static struct irqaction cmci_irqaction = {
         .handler =      ia64_mca_cmc_int_handler,
-        .flags =        IRQF_DISABLED,
         .name =         "cmc_hndlr"
 };
 
 static struct irqaction cmcp_irqaction = {
         .handler =      ia64_mca_cmc_int_caller,
-        .flags =        IRQF_DISABLED,
         .name =         "cmc_poll"
 };
 
 static struct irqaction mca_rdzv_irqaction = {
         .handler =      ia64_mca_rendez_int_handler,
-        .flags =        IRQF_DISABLED,
         .name =         "mca_rdzv"
 };
 
 static struct irqaction mca_wkup_irqaction = {
         .handler =      ia64_mca_wakeup_int_handler,
-        .flags =        IRQF_DISABLED,
         .name =         "mca_wkup"
 };
 
 #ifdef CONFIG_ACPI
 static struct irqaction mca_cpe_irqaction = {
         .handler =      ia64_mca_cpe_int_handler,
-        .flags =        IRQF_DISABLED,
         .name =         "cpe_hndlr"
 };
 
 static struct irqaction mca_cpep_irqaction = {
         .handler =      ia64_mca_cpe_int_caller,
-        .flags =        IRQF_DISABLED,
         .name =         "cpe_poll"
 };
 #endif /* CONFIG_ACPI */
diff --git a/arch/ia64/kernel/msi_ia64.c b/arch/ia64/kernel/msi_ia64.c
index fb2f1e622877..c430f9198d1b 100644
--- a/arch/ia64/kernel/msi_ia64.c
+++ b/arch/ia64/kernel/msi_ia64.c
@@ -17,12 +17,9 @@ static int ia64_set_msi_irq_affinity(struct irq_data *idata,
 {
         struct msi_msg msg;
         u32 addr, data;
-        int cpu = first_cpu(*cpu_mask);
+        int cpu = cpumask_first_and(cpu_mask, cpu_online_mask);
         unsigned int irq = idata->irq;
 
-        if (!cpu_online(cpu))
-                return -1;
-
         if (irq_prepare_move(irq, cpu))
                 return -1;
 
@@ -139,10 +136,7 @@ static int dmar_msi_set_affinity(struct irq_data *data,
         unsigned int irq = data->irq;
         struct irq_cfg *cfg = irq_cfg + irq;
         struct msi_msg msg;
-        int cpu = cpumask_first(mask);
-
-        if (!cpu_online(cpu))
-                return -1;
+        int cpu = cpumask_first_and(mask, cpu_online_mask);
 
         if (irq_prepare_move(irq, cpu))
                 return -1;
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index cb592773c78b..d841c4bd6864 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -6387,7 +6387,6 @@ pfm_flush_pmds(struct task_struct *task, pfm_context_t *ctx)
 
 static struct irqaction perfmon_irqaction = {
         .handler = pfm_interrupt_handler,
-        .flags   = IRQF_DISABLED,
         .name    = "perfmon"
 };
 
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index fbaac1afb844..71c52bc7c28d 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -380,7 +380,7 @@ static cycle_t itc_get_cycles(struct clocksource *cs)
 
 static struct irqaction timer_irqaction = {
         .handler =      timer_interrupt,
-        .flags =        IRQF_DISABLED | IRQF_IRQPOLL,
+        .flags =        IRQF_IRQPOLL,
         .name =         "timer"
 };
 
diff --git a/arch/ia64/kernel/uncached.c b/arch/ia64/kernel/uncached.c
index a96bcf83a735..20e8a9b21d75 100644
--- a/arch/ia64/kernel/uncached.c
+++ b/arch/ia64/kernel/uncached.c
@@ -98,7 +98,7 @@ static int uncached_add_chunk(struct uncached_pool *uc_pool, int nid)
         /* attempt to allocate a granule's worth of cached memory pages */
 
         page = alloc_pages_exact_node(nid,
-                                GFP_KERNEL | __GFP_ZERO | GFP_THISNODE,
+                                GFP_KERNEL | __GFP_ZERO | __GFP_THISNODE,
                                 IA64_GRANULE_SHIFT-PAGE_SHIFT);
         if (!page) {
                 mutex_unlock(&uc_pool->add_chunk_mutex);
diff --git a/arch/ia64/sn/kernel/irq.c b/arch/ia64/sn/kernel/irq.c
index 62cf4dde6a04..85d095154902 100644
--- a/arch/ia64/sn/kernel/irq.c
+++ b/arch/ia64/sn/kernel/irq.c
@@ -209,8 +209,8 @@ static int sn_set_affinity_irq(struct irq_data *data,
         nasid_t nasid;
         int slice;
 
-        nasid = cpuid_to_nasid(cpumask_first(mask));
-        slice = cpuid_to_slice(cpumask_first(mask));
+        nasid = cpuid_to_nasid(cpumask_first_and(mask, cpu_online_mask));
+        slice = cpuid_to_slice(cpumask_first_and(mask, cpu_online_mask));
 
         list_for_each_entry_safe(sn_irq_info, sn_irq_info_safe,
                                  sn_irq_lh[irq], list)
diff --git a/arch/ia64/sn/kernel/msi_sn.c b/arch/ia64/sn/kernel/msi_sn.c
index 2b98b9e088de..afc58d2799ad 100644
--- a/arch/ia64/sn/kernel/msi_sn.c
+++ b/arch/ia64/sn/kernel/msi_sn.c
@@ -166,7 +166,7 @@ static int sn_set_msi_irq_affinity(struct irq_data *data,
         struct sn_pcibus_provider *provider;
         unsigned int cpu, irq = data->irq;
 
-        cpu = cpumask_first(cpu_mask);
+        cpu = cpumask_first_and(cpu_mask, cpu_online_mask);
         sn_irq_info = sn_msi_info[irq].sn_irq_info;
         if (sn_irq_info == NULL || sn_irq_info->irq_int_bit >= 0)
                 return -1;
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index 932435ac4e5c..67779a74b62d 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -1,7 +1,9 @@
 
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += exec.h
+generic-y += hash.h
+generic-y += mcs_spinlock.h
 generic-y += module.h
-generic-y += trace_clock.h
 generic-y += preempt.h
-generic-y += hash.h
+generic-y += trace_clock.h
diff --git a/arch/m32r/include/asm/cputime.h b/arch/m32r/include/asm/cputime.h
deleted file mode 100644
index 0a47550df2b7..000000000000
--- a/arch/m32r/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __M32R_CPUTIME_H
-#define __M32R_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __M32R_CPUTIME_H */
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index dbdd2231c75d..b2e322939256 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -17,6 +17,7 @@ config M68K
         select FPU if MMU
         select ARCH_WANT_IPC_PARSE_VERSION
         select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
+        select HAVE_FUTEX_CMPXCHG if MMU && FUTEX
         select HAVE_MOD_ARCH_SPECIFIC
         select MODULES_USE_ELF_REL
         select MODULES_USE_ELF_RELA
diff --git a/arch/m68k/amiga/cia.c b/arch/m68k/amiga/cia.c
index 18c0e29976e3..2081b8cd5591 100644
--- a/arch/m68k/amiga/cia.c
+++ b/arch/m68k/amiga/cia.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 
 #include <asm/irq.h>
 #include <asm/amigahw.h>
diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c
index 3e73a63c066f..3d2b63bedf05 100644
--- a/arch/m68k/atari/ataints.c
+++ b/arch/m68k/atari/ataints.c
@@ -41,6 +41,7 @@
 #include <linux/init.h>
 #include <linux/seq_file.h>
 #include <linux/module.h>
+#include <linux/irq.h>
 
 #include <asm/traps.h>
 
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index 559ff3af8ff7..96da4963d14b 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -24,6 +24,8 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -85,6 +87,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -94,6 +97,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -126,6 +131,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -163,8 +169,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -190,7 +194,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -512,7 +515,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index cb1f55df69b6..1b8739f50cbf 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -25,6 +25,8 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -83,6 +85,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -92,6 +95,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -124,6 +129,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -161,8 +167,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -188,7 +192,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -470,7 +473,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index e880cfbb62d9..6ea4e91f0caa 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -24,6 +24,8 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -82,6 +84,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -91,6 +94,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -123,6 +128,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -160,8 +166,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -187,7 +191,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -487,7 +490,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 4aa4f45e52a8..e5a12739ff2d 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -24,6 +24,8 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
 CONFIG_M68060=y
 CONFIG_VME=y
@@ -81,6 +83,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -90,6 +93,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -122,6 +127,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -159,8 +165,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -186,7 +190,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -463,7 +466,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 7cd9d9f456fb..8936d7fb0f0f 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -25,6 +25,8 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -83,6 +85,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -92,6 +95,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -124,6 +129,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -161,8 +167,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -188,7 +192,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -472,7 +475,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index 31f5bd061d14..be5342cca25b 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -24,6 +24,8 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68030=y
 CONFIG_M68040=y
@@ -82,6 +84,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -91,6 +94,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -123,6 +128,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -160,8 +166,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -187,7 +191,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -495,7 +498,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 4e5adff326ee..f27194ade167 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -20,6 +20,8 @@ CONFIG_SOLARIS_X86_PARTITION=y
 CONFIG_UNIXWARE_DISKLABEL=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68020=y
 CONFIG_M68040=y
 CONFIG_M68060=y
@@ -91,6 +93,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -100,6 +103,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -132,6 +137,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -169,8 +175,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -196,7 +200,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -571,7 +574,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 02cdbac5565e..c3887603c1db 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -24,6 +24,8 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68030=y
 CONFIG_VME=y
 CONFIG_MVME147=y
@@ -80,6 +82,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -89,6 +92,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -121,6 +126,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -158,8 +164,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -185,7 +189,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -463,7 +466,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 05a990a9dbd4..f7ff784d05ac 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -24,6 +24,8 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
 CONFIG_M68060=y
 CONFIG_VME=y
@@ -81,6 +83,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -90,6 +93,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -122,6 +127,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -159,8 +165,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -186,7 +190,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -464,7 +467,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 568e2a98f976..f0c72ab037be 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -25,6 +25,8 @@ CONFIG_SUN_PARTITION=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_M68040=y
 CONFIG_M68060=y
 CONFIG_Q40=y
@@ -81,6 +83,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -90,6 +93,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -122,6 +127,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -159,8 +165,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -186,7 +190,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -485,7 +488,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index 60b0aeac5742..7bca0f464521 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -24,6 +24,8 @@ CONFIG_UNIXWARE_DISKLABEL=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_SUN3=y
 # CONFIG_COMPACTION is not set
 CONFIG_CLEANCACHE=y
@@ -78,6 +80,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -87,6 +90,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -119,6 +124,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -156,8 +162,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -183,7 +187,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -464,7 +467,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index 21bda331eebb..317f3e1fec95 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -24,6 +24,8 @@ CONFIG_UNIXWARE_DISKLABEL=y
 # CONFIG_EFI_PARTITION is not set
 CONFIG_SYSV68_PARTITION=y
 CONFIG_IOSCHED_DEADLINE=m
+CONFIG_KEXEC=y
+CONFIG_BOOTINFO_PROC=y
 CONFIG_SUN3X=y
 # CONFIG_COMPACTION is not set
 CONFIG_CLEANCACHE=y
@@ -78,6 +80,7 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_INET=m
 CONFIG_NFT_EXTHDR=m
 CONFIG_NFT_META=m
 CONFIG_NFT_CT=m
@@ -87,6 +90,8 @@ CONFIG_NFT_COUNTER=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_NAT=m
+CONFIG_NFT_QUEUE=m
+CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -119,6 +124,7 @@ CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
+CONFIG_NETFILTER_XT_MATCH_IPCOMP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
@@ -156,8 +162,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_TABLES_IPV4=m
-CONFIG_NFT_REJECT_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_CHAIN_NAT_IPV4=m
 CONFIG_NF_TABLES_ARP=m
@@ -183,7 +187,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_TABLES_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
@@ -464,7 +467,6 @@ CONFIG_CRYPTO_LZ4HC=m
 CONFIG_CRYPTO_USER_API_HASH=m
 CONFIG_CRYPTO_USER_API_SKCIPHER=m
 # CONFIG_CRYPTO_HW is not set
-CONFIG_CRC_T10DIF=y
 CONFIG_XZ_DEC_X86=y
 CONFIG_XZ_DEC_POWERPC=y
 CONFIG_XZ_DEC_IA64=y
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 7cc8c364924d..c67c94a2d672 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,4 +1,4 @@
-
+generic-y += barrier.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
 generic-y += cputime.h
@@ -6,6 +6,7 @@ generic-y += device.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
@@ -13,11 +14,13 @@ generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
-generic-y += local64.h
 generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += mman.h
 generic-y += mutex.h
 generic-y += percpu.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
@@ -31,5 +34,3 @@ generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h
deleted file mode 100644
index 15c5f77c1614..000000000000
--- a/arch/m68k/include/asm/barrier.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _M68K_BARRIER_H
-#define _M68K_BARRIER_H
-
-#define nop()           do { asm volatile ("nop"); barrier(); } while (0)
-
-#include <asm-generic/barrier.h>
-
-#endif /* _M68K_BARRIER_H */
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index 014f288fc813..9d38b73989eb 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -4,7 +4,7 @@
 #include <uapi/asm/unistd.h>
 
 
-#define NR_syscalls             349
+#define NR_syscalls             351
 
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/m68k/include/uapi/asm/unistd.h b/arch/m68k/include/uapi/asm/unistd.h
index 625f321001dc..b932dd470041 100644
--- a/arch/m68k/include/uapi/asm/unistd.h
+++ b/arch/m68k/include/uapi/asm/unistd.h
@@ -354,5 +354,7 @@
 #define __NR_process_vm_writev  346
 #define __NR_kcmp               347
 #define __NR_finit_module       348
+#define __NR_sched_setattr      349
+#define __NR_sched_getattr      350
 
 #endif /* _UAPI_ASM_M68K_UNISTD_H_ */
diff --git a/arch/m68k/kernel/head.S b/arch/m68k/kernel/head.S
index 4c99bab7e664..3ab329b88521 100644
--- a/arch/m68k/kernel/head.S
+++ b/arch/m68k/kernel/head.S
@@ -275,7 +275,6 @@
 
 #ifdef CONFIG_FRAMEBUFFER_CONSOLE
 #define CONSOLE
-#define CONSOLE_PENGUIN
 #endif
 
 #ifdef CONFIG_EARLY_PRINTK
@@ -658,27 +657,6 @@ ENTRY(__start)
         movel   %a0@,%a1@
 #endif
 
-#if 0
-        /*
-         * Clear the screen
-         */
-        lea     %pc@(L(mac_videobase)),%a0
-        movel   %a0@,%a1
-        lea     %pc@(L(mac_dimensions)),%a0
-        movel   %a0@,%d1
-        swap    %d1             /* #rows is high bytes */
-        andl    #0xFFFF,%d1     /* rows */
-        subl    #10,%d1
-        lea     %pc@(L(mac_rowbytes)),%a0
-loopy2:
-        movel   %a0@,%d0
-        subql   #1,%d0
-loopx2:
-        moveb   #0x55, %a1@+
-        dbra    %d0,loopx2
-        dbra    %d1,loopy2
-#endif
-
 L(test_notmac):
 #endif /* CONFIG_MAC */
 
@@ -907,15 +885,15 @@ L(nothp):
  */
 #ifdef CONFIG_MAC
         is_not_mac(L(nocon))
-#ifdef CONSOLE
+#  ifdef CONSOLE
         console_init
-#ifdef CONSOLE_PENGUIN
+#    ifdef CONFIG_LOGO
         console_put_penguin
-#endif  /* CONSOLE_PENGUIN */
+#    endif /* CONFIG_LOGO */
         console_put_stats
-#endif  /* CONSOLE */
+#  endif /* CONSOLE */
 L(nocon):
-#endif  /* CONFIG_MAC */
+#endif /* CONFIG_MAC */
 
 
         putc    '\n'
@@ -3324,14 +3302,13 @@ func_return	set_leds
 #define Lconsole_struct_num_columns     8
 #define Lconsole_struct_num_rows        12
 #define Lconsole_struct_left_edge       16
-#define Lconsole_struct_penguin_putc    20
 
 func_start      console_init,%a0-%a4/%d0-%d7
         /*
          *      Some of the register usage that follows
          *              a0 = pointer to boot_info
          *              a1 = pointer to screen
-         *              a2 = pointer to Lconsole_globals
+         *              a2 = pointer to console_globals
          *              d3 = pixel width of screen
          *              d4 = pixel height of screen
          *              (d3,d4) ~= (x,y) of a point just below
@@ -3456,7 +3433,7 @@ func_start	console_put_stats,%a0/%d7
 
 func_return     console_put_stats
 
-#ifdef CONSOLE_PENGUIN
+#ifdef CONFIG_LOGO
 func_start      console_put_penguin,%a0-%a1/%d0-%d7
         /*
          *      Get 'that_penguin' onto the screen in the upper right corner
@@ -3799,38 +3776,6 @@ L(console_plot_pixel_exit):
 func_return     console_plot_pixel
 #endif /* CONSOLE */
 
-#if 0
-/*
- * This is some old code lying around.  I don't believe
- * it's used or important anymore.  My guess is it contributed
- * to getting to this point, but it's done for now.
- * It was still in the 2.1.77 head.S, so it's still here.
- * (And still not used!)
- */
-L(showtest):
-        moveml  %a0/%d7,%sp@-
-        puts    "A="
-        putn    %a1
-
-        .long   0xf0119f15              | ptestr        #5,%a1@,#7,%a0
-
-        puts    "DA="
-        putn    %a0
-
-        puts    "D="
-        putn    %a0@
-
-        puts    "S="
-        lea     %pc@(L(mmu)),%a0
-        .long   0xf0106200              | pmove         %psr,%a0@
-        clrl    %d7
-        movew   %a0@,%d7
-        putn    %d7
-
-        putc    '\n'
-        moveml  %sp@+,%a0/%d7
-        rts
-#endif  /* 0 */
 
 __INITDATA
         .align  4
@@ -3849,7 +3794,6 @@ L(console_globals):
         .long   0               /* max num columns */
         .long   0               /* max num rows */
         .long   0               /* left edge */
-        .long   0               /* mac putc */
 L(console_font):
         .long   0               /* pointer to console font (struct font_desc) */
 L(console_font_data):
diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c
index 077d3a70fed1..5b8d66fbf383 100644
--- a/arch/m68k/kernel/ints.c
+++ b/arch/m68k/kernel/ints.c
@@ -10,9 +10,9 @@
 #include <linux/types.h>
 #include <linux/sched.h>
 #include <linux/interrupt.h>
-#include <linux/kernel_stat.h>
 #include <linux/errno.h>
 #include <linux/init.h>
+#include <linux/irq.h>
 
 #include <asm/setup.h>
 #include <asm/irq.h>
diff --git a/arch/m68k/kernel/syscalltable.S b/arch/m68k/kernel/syscalltable.S
index 3f04ea0ab802..b6223dc41d82 100644
--- a/arch/m68k/kernel/syscalltable.S
+++ b/arch/m68k/kernel/syscalltable.S
@@ -369,4 +369,6 @@ ENTRY(sys_call_table)
         .long sys_process_vm_writev
         .long sys_kcmp
         .long sys_finit_module
+        .long sys_sched_setattr
+        .long sys_sched_getattr         /* 350 */
 
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index b716d807c2ec..c29ead89a317 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -13,6 +13,7 @@ generic-y += fb.h
 generic-y += fcntl.h
 generic-y += futex.h
 generic-y += hardirq.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
@@ -23,6 +24,7 @@ generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += param.h
@@ -30,6 +32,7 @@ generic-y += pci.h
 generic-y += percpu.h
 generic-y += poll.h
 generic-y += posix_types.h
+generic-y += preempt.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += sembuf.h
@@ -52,5 +55,3 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 2b98bc73642a..c98ed95c0541 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -1,8 +1,10 @@
 
 generic-y += barrier.h
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
-generic-y += trace_clock.h
-generic-y += syscalls.h
+generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += syscalls.h
+generic-y += trace_clock.h
diff --git a/arch/microblaze/include/asm/cputime.h b/arch/microblaze/include/asm/cputime.h
deleted file mode 100644
index 6d68ad7e0ea3..000000000000
--- a/arch/microblaze/include/asm/cputime.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/cputime.h>
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index dcae3a7035db..95fa1f1d5c8b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1776,12 +1776,12 @@ endchoice
 
 config FORCE_MAX_ZONEORDER
         int "Maximum zone order"
-        range 14 64 if HUGETLB_PAGE && PAGE_SIZE_64KB
-        default "14" if HUGETLB_PAGE && PAGE_SIZE_64KB
-        range 13 64 if HUGETLB_PAGE && PAGE_SIZE_32KB
-        default "13" if HUGETLB_PAGE && PAGE_SIZE_32KB
-        range 12 64 if HUGETLB_PAGE && PAGE_SIZE_16KB
-        default "12" if HUGETLB_PAGE && PAGE_SIZE_16KB
+        range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+        default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+        range 13 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+        default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+        range 12 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
+        default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
         range 11 64
         default "11"
         help
@@ -2353,9 +2353,8 @@ config SECCOMP
           If unsure, say Y. Only embedded should say N here.
 
 config MIPS_O32_FP64_SUPPORT
-        bool "Support for O32 binaries using 64-bit FP"
+        bool "Support for O32 binaries using 64-bit FP (EXPERIMENTAL)"
         depends on 32BIT || MIPS32_O32
-        default y
         help
           When this is enabled, the kernel will support use of 64-bit floating
           point registers with binaries using the O32 ABI along with the
@@ -2367,7 +2366,14 @@ config MIPS_O32_FP64_SUPPORT
           of your kernel & potentially improve FP emulation performance by
           saying N here.
 
-          If unsure, say Y.
+          Although binutils currently supports use of this flag the details
+          concerning its effect upon the O32 ABI in userland are still being
+          worked on. In order to avoid userland becoming dependant upon current
+          behaviour before the details have been finalised, this option should
+          be considered experimental and only enabled by those working upon
+          said details.
+
+          If unsure, say N.
 
 config USE_OF
         bool
diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index 9edc35ff8cf1..acf9a2a37f5a 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -53,10 +53,8 @@ void __init prom_init(void)
         prom_init_cmdline();
 
         memsize_str = prom_getenv("memsize");
-        if (!memsize_str)
+        if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
                 memsize = 0x04000000;
-        else
-                strict_strtoul(memsize_str, 0, &memsize);
         add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index 9969dbab19e3..25a59a23547e 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -52,10 +52,8 @@ void __init prom_init(void)
         prom_init_cmdline();
 
         memsize_str = prom_getenv("memsize");
-        if (!memsize_str)
+        if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
                 memsize = 0x04000000;
-        else
-                strict_strtoul(memsize_str, 0, &memsize);
         add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c
index 6d612e2b949b..cdd8246f92b3 100644
--- a/arch/mips/bcm47xx/board.c
+++ b/arch/mips/bcm47xx/board.c
@@ -1,3 +1,4 @@
+#include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/string.h>
 #include <bcm47xx_board.h>
diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c
index 6decb27cf48b..2bed73a684ae 100644
--- a/arch/mips/bcm47xx/nvram.c
+++ b/arch/mips/bcm47xx/nvram.c
@@ -196,7 +196,7 @@ int bcm47xx_nvram_gpio_pin(const char *name)
         char nvram_var[10];
         char buf[30];
 
-        for (i = 0; i < 16; i++) {
+        for (i = 0; i < 32; i++) {
                 err = snprintf(nvram_var, sizeof(nvram_var), "gpio%i", i);
                 if (err <= 0)
                         continue;
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 25fbfae06c1f..c2bb4f896ce7 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -975,10 +975,6 @@ static int octeon_irq_ciu_xlat(struct irq_domain *d,
         if (ciu > 1 || bit > 63)
                 return -EINVAL;
 
-        /* These are the GPIO lines */
-        if (ciu == 0 && bit >= 16 && bit < 32)
-                return -EINVAL;
-
         *out_hwirq = (ciu << 6) | bit;
         *out_type = 0;
 
@@ -1007,6 +1003,10 @@ static int octeon_irq_ciu_map(struct irq_domain *d,
         if (!octeon_irq_virq_in_range(virq))
                 return -EINVAL;
 
+        /* Don't map irq if it is reserved for GPIO. */
+        if (line == 0 && bit >= 16 && bit <32)
+                return 0;
+
         if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0)
                 return -EINVAL;
 
@@ -1525,10 +1525,6 @@ static int octeon_irq_ciu2_xlat(struct irq_domain *d,
         ciu = intspec[0];
         bit = intspec[1];
 
-        /* Line 7  are the GPIO lines */
-        if (ciu > 6 || bit > 63)
-                return -EINVAL;
-
         *out_hwirq = (ciu << 6) | bit;
         *out_type = 0;
 
@@ -1570,8 +1566,14 @@ static int octeon_irq_ciu2_map(struct irq_domain *d,
         if (!octeon_irq_virq_in_range(virq))
                 return -EINVAL;
 
-        /* Line 7  are the GPIO lines */
-        if (line > 6 || octeon_irq_ciu_to_irq[line][bit] != 0)
+        /*
+         * Don't map irq if it is reserved for GPIO.
+         * (Line 7 are the GPIO lines.)
+         */
+        if (line == 7)
+                return 0;
+
+        if (line > 7 || octeon_irq_ciu_to_irq[line][bit] != 0)
                 return -EINVAL;
 
         if (octeon_irq_ciu2_is_edge(line, bit))
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 2d7f65052c1f..05439187891d 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -2,16 +2,17 @@
 generic-y += cputime.h
 generic-y += current.h
 generic-y += emergency-restart.h
+generic-y += hash.h
 generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += mutex.h
 generic-y += parport.h
 generic-y += percpu.h
+generic-y += preempt.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += segment.h
 generic-y += serial.h
 generic-y += trace_clock.h
-generic-y += preempt.h
 generic-y += ucontext.h
 generic-y += xor.h
-generic-y += hash.h
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 3220c93ea981..4225e99bd7bf 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -9,6 +9,7 @@
 #define _ASM_ASMMACRO_H
 
 #include <asm/hazards.h>
+#include <asm/asm-offsets.h>
 
 #ifdef CONFIG_32BIT
 #include <asm/asmmacro-32.h>
@@ -54,11 +55,21 @@
         .endm
 
         .macro  local_irq_disable reg=t0
+#ifdef CONFIG_PREEMPT
+        lw      \reg, TI_PRE_COUNT($28)
+        addi    \reg, \reg, 1
+        sw      \reg, TI_PRE_COUNT($28)
+#endif
         mfc0    \reg, CP0_STATUS
         ori     \reg, \reg, 1
         xori    \reg, \reg, 1
         mtc0    \reg, CP0_STATUS
         irq_disable_hazard
+#ifdef CONFIG_PREEMPT
+        lw      \reg, TI_PRE_COUNT($28)
+        addi    \reg, \reg, -1
+        sw      \reg, TI_PRE_COUNT($28)
+#endif
         .endm
 #endif /* CONFIG_MIPS_MT_SMTC */
 
@@ -106,7 +117,7 @@
         .endm
 
         .macro  fpu_save_double thread status tmp
-#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
         sll     \tmp, \status, 5
         bgez    \tmp, 10f
         fpu_save_16odd \thread
@@ -159,7 +170,7 @@
         .endm
 
         .macro  fpu_restore_double thread status tmp
-#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
         sll     \tmp, \status, 5
         bgez    \tmp, 10f                               # 16 register mode?
 
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 6b9749540edf..58e50cbdb1a6 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -57,7 +57,7 @@ static inline int __enable_fpu(enum fpu_mode mode)
                 return 0;
 
         case FPU_64BIT:
-#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_MIPS64))
+#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_64BIT))
                 /* we only have a 32-bit FPU */
                 return SIGFPE;
 #endif
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index ce35c9af0c28..992aaba603b5 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -22,12 +22,12 @@ extern void _mcount(void);
 #define safe_load(load, src, dst, error)                \
 do {                                                    \
         asm volatile (                                  \
-                "1: " load " %[" STR(dst) "], 0(%[" STR(src) "])\n"\
-                "   li %[" STR(error) "], 0\n"          \
+                "1: " load " %[tmp_dst], 0(%[tmp_src])\n"       \
+                "   li %[tmp_err], 0\n"                 \
                 "2:\n"                                  \
                                                         \
                 ".section .fixup, \"ax\"\n"             \
-                "3: li %[" STR(error) "], 1\n"          \
+                "3: li %[tmp_err], 1\n"                 \
                 "   j 2b\n"                             \
                 ".previous\n"                           \
                                                         \
@@ -35,8 +35,8 @@ do {							\
                 STR(PTR) "\t1b, 3b\n\t"                 \
                 ".previous\n"                           \
                                                         \
-                : [dst] "=&r" (dst), [error] "=r" (error)\
-                : [src] "r" (src)                       \
+                : [tmp_dst] "=&r" (dst), [tmp_err] "=r" (error)\
+                : [tmp_src] "r" (src)                   \
                 : "memory"                              \
         );                                              \
 } while (0)
@@ -44,12 +44,12 @@ do {							\
 #define safe_store(store, src, dst, error)      \
 do {                                            \
         asm volatile (                          \
-                "1: " store " %[" STR(src) "], 0(%[" STR(dst) "])\n"\
-                "   li %[" STR(error) "], 0\n"  \
+                "1: " store " %[tmp_src], 0(%[tmp_dst])\n"\
+                "   li %[tmp_err], 0\n"         \
                 "2:\n"                          \
                                                 \
                 ".section .fixup, \"ax\"\n"     \
-                "3: li %[" STR(error) "], 1\n"  \
+                "3: li %[tmp_err], 1\n"         \
                 "   j 2b\n"                     \
                 ".previous\n"                   \
                                                 \
@@ -57,8 +57,8 @@ do {						\
                 STR(PTR) "\t1b, 3b\n\t"         \
                 ".previous\n"                   \
                                                 \
-                : [error] "=r" (error)          \
-                : [dst] "r" (dst), [src] "r" (src)\
+                : [tmp_err] "=r" (error)        \
+                : [tmp_dst] "r" (dst), [tmp_src] "r" (src)\
                 : "memory"                      \
         );                                      \
 } while (0)
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 33e8dbfc1b63..f35b131977e6 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -13,6 +13,7 @@
 #ifndef __ASM_MIPS_SYSCALL_H
 #define __ASM_MIPS_SYSCALL_H
 
+#include <linux/compiler.h>
 #include <linux/audit.h>
 #include <linux/elf-em.h>
 #include <linux/kernel.h>
@@ -39,14 +40,14 @@ static inline unsigned long mips_get_syscall_arg(unsigned long *arg,
 
 #ifdef CONFIG_32BIT
         case 4: case 5: case 6: case 7:
-                return get_user(*arg, (int *)usp + 4 * n);
+                return get_user(*arg, (int *)usp + n);
 #endif
 
 #ifdef CONFIG_64BIT
         case 4: case 5: case 6: case 7:
 #ifdef CONFIG_MIPS32_O32
                 if (test_thread_flag(TIF_32BIT_REGS))
-                        return get_user(*arg, (int *)usp + 4 * n);
+                        return get_user(*arg, (int *)usp + n);
                 else
 #endif
                         *arg = regs->regs[4 + n];
@@ -57,6 +58,8 @@ static inline unsigned long mips_get_syscall_arg(unsigned long *arg,
         default:
                 BUG();
         }
+
+        unreachable();
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
@@ -83,11 +86,10 @@ static inline void syscall_get_arguments(struct task_struct *task,
                                          unsigned int i, unsigned int n,
                                          unsigned long *args)
 {
-        unsigned long arg;
         int ret;
 
         while (n--)
-                ret |= mips_get_syscall_arg(&arg, task, regs, i++);
+                ret |= mips_get_syscall_arg(args++, task, regs, i++);
 
         /*
          * No way to communicate an error because this is a void function.
diff --git a/arch/mips/include/asm/topology.h b/arch/mips/include/asm/topology.h
index 12609a17dc8b..20ea4859c822 100644
--- a/arch/mips/include/asm/topology.h
+++ b/arch/mips/include/asm/topology.h
@@ -10,8 +10,4 @@
 
 #include <topology.h>
 
-#ifdef CONFIG_SMP
-#define smt_capable()   (smp_num_siblings > 1)
-#endif
-
 #endif /* __ASM_TOPOLOGY_H */
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index 4d3b92886665..413d6c612bec 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -24,7 +24,6 @@
 
 #ifndef __ASSEMBLY__
 
-#define __ARCH_OMIT_COMPAT_SYS_GETDENTS64
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index b39ba25b41cc..f25181b19941 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -163,8 +163,8 @@ enum cop1_sdw_func {
  */
 enum cop1x_func {
         lwxc1_op     =  0x00, ldxc1_op     =  0x01,
-        pfetch_op    =  0x07, swxc1_op     =  0x08,
-        sdxc1_op     =  0x09, madd_s_op    =  0x20,
+        swxc1_op     =  0x08, sdxc1_op     =  0x09,
+        pfetch_op    =  0x0f, madd_s_op    =  0x20,
         madd_d_op    =  0x21, madd_e_op    =  0x22,
         msub_s_op    =  0x28, msub_d_op    =  0x29,
         msub_e_op    =  0x2a, nmadd_s_op   =  0x30,
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 185ba258361b..374ed74cd516 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -111,11 +111,10 @@ static int ftrace_modify_code_2(unsigned long ip, unsigned int new_code1,
         safe_store_code(new_code1, ip, faulted);
         if (unlikely(faulted))
                 return -EFAULT;
-        ip += 4;
-        safe_store_code(new_code2, ip, faulted);
+        safe_store_code(new_code2, ip + 4, faulted);
         if (unlikely(faulted))
                 return -EFAULT;
-        flush_icache_range(ip, ip + 8); /* original ip + 12 */
+        flush_icache_range(ip, ip + 8);
         return 0;
 }
 #endif
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 253b2fb52026..73b0ddf910d4 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -35,9 +35,9 @@
 LEAF(_save_fp_context)
         cfc1    t1, fcr31
 
-#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
         .set    push
-#ifdef CONFIG_MIPS32_R2
+#ifdef CONFIG_CPU_MIPS32_R2
         .set    mips64r2
         mfc0    t0, CP0_STATUS
         sll     t0, t0, 5
@@ -146,11 +146,11 @@ LEAF(_save_fp_context32)
  *  - cp1 status/control register
  */
 LEAF(_restore_fp_context)
-        EX      lw t0, SC_FPC_CSR(a0)
+        EX      lw t1, SC_FPC_CSR(a0)
 
-#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
         .set    push
-#ifdef CONFIG_MIPS32_R2
+#ifdef CONFIG_CPU_MIPS32_R2
         .set    mips64r2
         mfc0    t0, CP0_STATUS
         sll     t0, t0, 5
@@ -191,7 +191,7 @@ LEAF(_restore_fp_context)
         EX      ldc1 $f26, SC_FPREGS+208(a0)
         EX      ldc1 $f28, SC_FPREGS+224(a0)
         EX      ldc1 $f30, SC_FPREGS+240(a0)
-        ctc1    t0, fcr31
+        ctc1    t1, fcr31
         jr      ra
          li     v0, 0                                   # success
         END(_restore_fp_context)
@@ -199,7 +199,7 @@ LEAF(_restore_fp_context)
 #ifdef CONFIG_MIPS32_COMPAT
 LEAF(_restore_fp_context32)
         /* Restore an o32 sigcontext.  */
-        EX      lw t0, SC32_FPC_CSR(a0)
+        EX      lw t1, SC32_FPC_CSR(a0)
 
         mfc0    t0, CP0_STATUS
         sll     t0, t0, 5
@@ -239,7 +239,7 @@ LEAF(_restore_fp_context32)
         EX      ldc1 $f26, SC32_FPREGS+208(a0)
         EX      ldc1 $f28, SC32_FPREGS+224(a0)
         EX      ldc1 $f30, SC32_FPREGS+240(a0)
-        ctc1    t0, fcr31
+        ctc1    t1, fcr31
         jr      ra
          li     v0, 0                                   # success
         END(_restore_fp_context32)
diff --git a/arch/mips/kernel/rtlx-cmp.c b/arch/mips/kernel/rtlx-cmp.c
index 56dc69635153..758fb3cd2326 100644
--- a/arch/mips/kernel/rtlx-cmp.c
+++ b/arch/mips/kernel/rtlx-cmp.c
@@ -112,5 +112,8 @@ void __exit rtlx_module_exit(void)
 
         for (i = 0; i < RTLX_CHANNELS; i++)
                 device_destroy(mt_class, MKDEV(major, i));
+
         unregister_chrdev(major, RTLX_MODULE_NAME);
+
+        aprp_hook = NULL;
 }
diff --git a/arch/mips/kernel/rtlx-mt.c b/arch/mips/kernel/rtlx-mt.c
index 91d61ba422b4..9c1aca00fd54 100644
--- a/arch/mips/kernel/rtlx-mt.c
+++ b/arch/mips/kernel/rtlx-mt.c
@@ -144,5 +144,8 @@ void __exit rtlx_module_exit(void)
 
         for (i = 0; i < RTLX_CHANNELS; i++)
                 device_destroy(mt_class, MKDEV(major, i));
+
         unregister_chrdev(major, RTLX_MODULE_NAME);
+
+        aprp_hook = NULL;
 }
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index dfc1b911be04..c1681d65dd5c 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -1007,7 +1007,7 @@ static void __irq_entry smtc_clock_tick_interrupt(void)
         int irq = MIPS_CPU_IRQ_BASE + 1;
 
         irq_enter();
-        kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+        kstat_incr_irq_this_cpu(irq);
         cd = &per_cpu(mips_clockevent_device, cpu);
         cd->event_handler(cd);
         irq_exit();
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 506925b2c3f3..0b4e2e38294b 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1538,10 +1538,10 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
                 break;
         }
 
-        case 0x7:               /* 7 */
-                if (MIPSInst_FUNC(ir) != pfetch_op) {
+        case 0x3:
+                if (MIPSInst_FUNC(ir) != pfetch_op)
                         return SIGILL;
-                }
+
                 /* ignore prefx operation */
                 break;
 
diff --git a/arch/mips/mti-malta/malta-amon.c b/arch/mips/mti-malta/malta-amon.c
index 592ac0427426..84ac523b0ce0 100644
--- a/arch/mips/mti-malta/malta-amon.c
+++ b/arch/mips/mti-malta/malta-amon.c
@@ -72,7 +72,7 @@ int amon_cpu_start(int cpu,
         return 0;
 }
 
-#ifdef CONFIG_MIPS_VPE_LOADER
+#ifdef CONFIG_MIPS_VPE_LOADER_CMP
 int vpe_run(struct vpe *v)
 {
         struct vpe_notifications *n;
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index ca3e3a46a42f..2242181a6284 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -119,7 +119,7 @@ static void malta_hw0_irqdispatch(void)
 
         do_IRQ(MALTA_INT_BASE + irq);
 
-#ifdef MIPS_VPE_APSP_API
+#ifdef CONFIG_MIPS_VPE_APSP_API_MT
         if (aprp_hook)
                 aprp_hook();
 #endif
@@ -310,7 +310,7 @@ static void ipi_call_dispatch(void)
 
 static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 {
-#ifdef MIPS_VPE_APSP_API
+#ifdef CONFIG_MIPS_VPE_APSP_API_CMP
         if (aprp_hook)
                 aprp_hook();
 #endif
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index d37be36dc659..2b91b0e61566 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -150,6 +150,7 @@ msi_irq_allocated:
                 msg.address_lo =
                         ((128ul << 20) + CVMX_PCI_MSI_RCV) & 0xffffffff;
                 msg.address_hi = ((128ul << 20) + CVMX_PCI_MSI_RCV) >> 32;
+                break;
         case OCTEON_DMA_BAR_TYPE_BIG:
                 /* When using big bar, Bar 0 is based at 0 */
                 msg.address_lo = (0 + CVMX_PCI_MSI_RCV) & 0xffffffff;
diff --git a/arch/mips/sgi-ip22/ip22-int.c b/arch/mips/sgi-ip22/ip22-int.c
index 3db64d51798d..58b40ae59335 100644
--- a/arch/mips/sgi-ip22/ip22-int.c
+++ b/arch/mips/sgi-ip22/ip22-int.c
@@ -148,7 +148,7 @@ static void __irq_entry indy_buserror_irq(void)
         int irq = SGI_BUSERR_IRQ;
 
         irq_enter();
-        kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+        kstat_incr_irq_this_cpu(irq);
         ip22_be_interrupt(irq);
         irq_exit();
 }
diff --git a/arch/mips/sgi-ip22/ip22-time.c b/arch/mips/sgi-ip22/ip22-time.c
index 607192449335..045aa89f28d8 100644
--- a/arch/mips/sgi-ip22/ip22-time.c
+++ b/arch/mips/sgi-ip22/ip22-time.c
@@ -123,7 +123,7 @@ void __irq_entry indy_8254timer_irq(void)
         char c;
 
         irq_enter();
-        kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+        kstat_incr_irq_this_cpu(irq);
         printk(KERN_ALERT "Oops, got 8254 interrupt.\n");
         ArcRead(0, &c, 1, &cnt);
         ArcEnterInteractiveMode();
diff --git a/arch/mips/sibyte/bcm1480/irq.c b/arch/mips/sibyte/bcm1480/irq.c
index 09d6e16a70f1..59cfe2659771 100644
--- a/arch/mips/sibyte/bcm1480/irq.c
+++ b/arch/mips/sibyte/bcm1480/irq.c
@@ -95,7 +95,7 @@ static int bcm1480_set_affinity(struct irq_data *d, const struct cpumask *mask,
         u64 cur_ints;
         unsigned long flags;
 
-        i = cpumask_first(mask);
+        i = cpumask_first_and(mask, cpu_online_mask);
 
         /* Convert logical CPU to physical CPU */
         cpu = cpu_logical_map(i);
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index 54e2c4de15c1..70d9182b26f1 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -182,7 +182,7 @@ void bcm1480_mailbox_interrupt(void)
         int irq = K_BCM1480_INT_MBOX_0_0;
         unsigned int action;
 
-        kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+        kstat_incr_irq_this_cpu(irq);
         /* Load the mailbox register to figure out what we're supposed to do */
         action = (__raw_readq(mailbox_0_regs[cpu]) >> 48) & 0xffff;
 
diff --git a/arch/mips/sibyte/sb1250/irq.c b/arch/mips/sibyte/sb1250/irq.c
index fca0cdb99509..6d8dba5cf348 100644
--- a/arch/mips/sibyte/sb1250/irq.c
+++ b/arch/mips/sibyte/sb1250/irq.c
@@ -88,7 +88,7 @@ static int sb1250_set_affinity(struct irq_data *d, const struct cpumask *mask,
         u64 cur_ints;
         unsigned long flags;
 
-        i = cpumask_first(mask);
+        i = cpumask_first_and(mask, cpu_online_mask);
 
         /* Convert logical CPU to physical CPU */
         cpu = cpu_logical_map(i);
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index d7b942db0ea5..db976117dd4d 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -170,7 +170,7 @@ void sb1250_mailbox_interrupt(void)
         int irq = K_INT_MBOX_0;
         unsigned int action;
 
-        kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+        kstat_incr_irq_this_cpu(irq);
         /* Load the mailbox register to figure out what we're supposed to do */
         action = (____raw_readq(mailbox_regs[cpu]) >> 48) & 0xffff;
 
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 992e989ab785..654d5ba6e310 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -1,7 +1,9 @@
 
 generic-y += barrier.h
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += exec.h
 generic-y += hash.h
-generic-y += trace_clock.h
+generic-y += mcs_spinlock.h
 generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/mn10300/include/asm/cputime.h b/arch/mn10300/include/asm/cputime.h
deleted file mode 100644
index 6d68ad7e0ea3..000000000000
--- a/arch/mn10300/include/asm/cputime.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/cputime.h>
diff --git a/arch/mn10300/kernel/cevt-mn10300.c b/arch/mn10300/kernel/cevt-mn10300.c
index ccce35e3e179..60f64ca1752a 100644
--- a/arch/mn10300/kernel/cevt-mn10300.c
+++ b/arch/mn10300/kernel/cevt-mn10300.c
@@ -113,7 +113,7 @@ int __init init_clockevents(void)
         cd->set_next_event      = next_event;
 
         iact = &per_cpu(timer_irq, cpu);
-        iact->flags = IRQF_DISABLED | IRQF_SHARED | IRQF_TIMER;
+        iact->flags = IRQF_SHARED | IRQF_TIMER;
         iact->handler = timer_interrupt;
 
         clockevents_register_device(cd);
diff --git a/arch/mn10300/kernel/mn10300-serial.c b/arch/mn10300/kernel/mn10300-serial.c
index bf6e949a2f87..7ecf69879e2d 100644
--- a/arch/mn10300/kernel/mn10300-serial.c
+++ b/arch/mn10300/kernel/mn10300-serial.c
@@ -985,17 +985,17 @@ static int mn10300_serial_startup(struct uart_port *_port)
         irq_set_chip(port->tm_irq, &mn10300_serial_pic);
 
         if (request_irq(port->rx_irq, mn10300_serial_interrupt,
-                        IRQF_DISABLED | IRQF_NOBALANCING,
+                        IRQF_NOBALANCING,
                         port->rx_name, port) < 0)
                 goto error;
 
         if (request_irq(port->tx_irq, mn10300_serial_interrupt,
-                        IRQF_DISABLED | IRQF_NOBALANCING,
+                        IRQF_NOBALANCING,
                         port->tx_name, port) < 0)
                 goto error2;
 
         if (request_irq(port->tm_irq, mn10300_serial_interrupt,
-                        IRQF_DISABLED | IRQF_NOBALANCING,
+                        IRQF_NOBALANCING,
                         port->tm_name, port) < 0)
                 goto error3;
         mn10300_serial_mask_ack(port->tm_irq);
diff --git a/arch/mn10300/kernel/mn10300-watchdog.c b/arch/mn10300/kernel/mn10300-watchdog.c
index db64a7166c09..a2d8e6938d67 100644
--- a/arch/mn10300/kernel/mn10300-watchdog.c
+++ b/arch/mn10300/kernel/mn10300-watchdog.c
@@ -142,7 +142,7 @@ void watchdog_interrupt(struct pt_regs *regs, enum exception_code excep)
         NMICR = NMICR_WDIF;
 
         nmi_count(smp_processor_id())++;
-        kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+        kstat_incr_irq_this_cpu(irq);
 
         for_each_online_cpu(cpu) {
 
diff --git a/arch/mn10300/kernel/smp.c b/arch/mn10300/kernel/smp.c
index a17f9c9c14c9..f984193718b1 100644
--- a/arch/mn10300/kernel/smp.c
+++ b/arch/mn10300/kernel/smp.c
@@ -143,7 +143,7 @@ static struct irqaction call_function_ipi = {
 static irqreturn_t smp_ipi_timer_interrupt(int irq, void *dev_id);
 static struct irqaction local_timer_ipi = {
         .handler        = smp_ipi_timer_interrupt,
-        .flags          = IRQF_DISABLED | IRQF_NOBALANCING,
+        .flags          = IRQF_NOBALANCING,
         .name           = "smp local timer IPI"
 };
 #endif
diff --git a/arch/mn10300/unit-asb2364/irq-fpga.c b/arch/mn10300/unit-asb2364/irq-fpga.c
index e16c216f31dc..073e2ccc4a44 100644
--- a/arch/mn10300/unit-asb2364/irq-fpga.c
+++ b/arch/mn10300/unit-asb2364/irq-fpga.c
@@ -76,7 +76,7 @@ static irqreturn_t fpga_interrupt(int irq, void *_mask)
 static struct irqaction fpga_irq[]  = {
         [0] = {
                 .handler        = fpga_interrupt,
-                .flags          = IRQF_DISABLED | IRQF_SHARED,
+                .flags          = IRQF_SHARED,
                 .name           = "fpga",
         },
 };
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 2e40f1ca8667..480af0d9c2f5 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -10,8 +10,8 @@ generic-y += bugs.h
 generic-y += cacheflush.h
 generic-y += checksum.h
 generic-y += clkdev.h
-generic-y += cmpxchg.h
 generic-y += cmpxchg-local.h
+generic-y += cmpxchg.h
 generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
@@ -25,6 +25,7 @@ generic-y += fcntl.h
 generic-y += ftrace.h
 generic-y += futex.h
 generic-y += hardirq.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
@@ -34,6 +35,7 @@ generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += kvm_para.h
 generic-y += local.h
+generic-y += mcs_spinlock.h
 generic-y += mman.h
 generic-y += module.h
 generic-y += msgbuf.h
@@ -41,6 +43,7 @@ generic-y += pci.h
 generic-y += percpu.h
 generic-y += poll.h
 generic-y += posix_types.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
@@ -53,11 +56,11 @@ generic-y += siginfo.h
 generic-y += signal.h
 generic-y += socket.h
 generic-y += sockios.h
-generic-y += statfs.h
 generic-y += stat.h
+generic-y += statfs.h
 generic-y += string.h
-generic-y += switch_to.h
 generic-y += swab.h
+generic-y += switch_to.h
 generic-y += termbits.h
 generic-y += termios.h
 generic-y += topology.h
@@ -68,5 +71,3 @@ generic-y += user.h
 generic-y += vga.h
 generic-y += word-at-a-time.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 752c981bc3c7..ecf25e6678ad 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -1,9 +1,29 @@
 
+generic-y += auxvec.h
 generic-y += barrier.h
-generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
-          segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \
-          div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
-          poll.h xor.h clkdev.h exec.h
-generic-y += trace_clock.h
-generic-y += preempt.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += device.h
+generic-y += div64.h
+generic-y += emergency-restart.h
+generic-y += exec.h
 generic-y += hash.h
+generic-y += hw_irq.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += kvm_para.h
+generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += mutex.h
+generic-y += param.h
+generic-y += percpu.h
+generic-y += poll.h
+generic-y += preempt.h
+generic-y += segment.h
+generic-y += topology.h
+generic-y += trace_clock.h
+generic-y += user.h
+generic-y += vga.h
+generic-y += word-at-a-time.h
+generic-y += xor.h
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index 637fe031aa84..60d5d174dfe4 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -32,17 +32,6 @@ void copy_page_asm(void *to, void *from);
 void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
                         struct page *pg);
 
-/* #define CONFIG_PARISC_TMPALIAS */
-
-#ifdef CONFIG_PARISC_TMPALIAS
-void clear_user_highpage(struct page *page, unsigned long vaddr);
-#define clear_user_highpage clear_user_highpage
-struct vm_area_struct;
-void copy_user_highpage(struct page *to, struct page *from,
-        unsigned long vaddr, struct vm_area_struct *vma);
-#define __HAVE_ARCH_COPY_USER_HIGHPAGE
-#endif
-
 /*
  * These are used to make use of C type-checking..
  */
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 3516e0b27044..64f2992e439f 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -191,8 +191,4 @@ static __inline__ int arch_write_can_lock(arch_rwlock_t *rw)
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
 
-#define arch_spin_relax(lock)   cpu_relax()
-#define arch_read_relax(lock)   cpu_relax()
-#define arch_write_relax(lock)  cpu_relax()
-
 #endif /* __ASM_SPINLOCK_H */
diff --git a/arch/parisc/include/uapi/asm/unistd.h b/arch/parisc/include/uapi/asm/unistd.h
index 42706794a36f..265ae5190b0a 100644
--- a/arch/parisc/include/uapi/asm/unistd.h
+++ b/arch/parisc/include/uapi/asm/unistd.h
@@ -828,13 +828,13 @@
 #define __NR_finit_module       (__NR_Linux + 333)
 #define __NR_sched_setattr      (__NR_Linux + 334)
 #define __NR_sched_getattr      (__NR_Linux + 335)
+#define __NR_utimes             (__NR_Linux + 336)
 
-#define __NR_Linux_syscalls     (__NR_sched_getattr + 1)
+#define __NR_Linux_syscalls     (__NR_utimes + 1)
 
 
 #define __IGNORE_select         /* newselect */
 #define __IGNORE_fadvise64      /* fadvise64_64 */
-#define __IGNORE_utimes         /* utime */
 
 
 #define HPUX_GATEWAY_ADDR       0xC0000004
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index ac87a40502e6..a6ffc775a9f8 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -581,67 +581,3 @@ flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long
                 __flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
         }
 }
-
-#ifdef CONFIG_PARISC_TMPALIAS
-
-void clear_user_highpage(struct page *page, unsigned long vaddr)
-{
-        void *vto;
-        unsigned long flags;
-
-        /* Clear using TMPALIAS region.  The page doesn't need to
-           be flushed but the kernel mapping needs to be purged.  */
-
-        vto = kmap_atomic(page);
-
-        /* The PA-RISC 2.0 Architecture book states on page F-6:
-           "Before a write-capable translation is enabled, *all*
-           non-equivalently-aliased translations must be removed
-           from the page table and purged from the TLB.  (Note
-           that the caches are not required to be flushed at this
-           time.)  Before any non-equivalent aliased translation
-           is re-enabled, the virtual address range for the writeable
-           page (the entire page) must be flushed from the cache,
-           and the write-capable translation removed from the page
-           table and purged from the TLB."  */
-
-        purge_kernel_dcache_page_asm((unsigned long)vto);
-        purge_tlb_start(flags);
-        pdtlb_kernel(vto);
-        purge_tlb_end(flags);
-        preempt_disable();
-        clear_user_page_asm(vto, vaddr);
-        preempt_enable();
-
-        pagefault_enable();             /* kunmap_atomic(addr, KM_USER0); */
-}
-
-void copy_user_highpage(struct page *to, struct page *from,
-        unsigned long vaddr, struct vm_area_struct *vma)
-{
-        void *vfrom, *vto;
-        unsigned long flags;
-
-        /* Copy using TMPALIAS region.  This has the advantage
-           that the `from' page doesn't need to be flushed.  However,
-           the `to' page must be flushed in copy_user_page_asm since
-           it can be used to bring in executable code.  */
-
-        vfrom = kmap_atomic(from);
-        vto = kmap_atomic(to);
-
-        purge_kernel_dcache_page_asm((unsigned long)vto);
-        purge_tlb_start(flags);
-        pdtlb_kernel(vto);
-        pdtlb_kernel(vfrom);
-        purge_tlb_end(flags);
-        preempt_disable();
-        copy_user_page_asm(vto, vfrom, vaddr);
-        flush_dcache_page_asm(__pa(vto), vaddr);
-        preempt_enable();
-
-        pagefault_enable();             /* kunmap_atomic(addr, KM_USER1); */
-        pagefault_enable();             /* kunmap_atomic(addr, KM_USER0); */
-}
-
-#endif /* CONFIG_PARISC_TMPALIAS */
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 8ceac4785609..cfe056fe7f5c 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -117,7 +117,7 @@ int cpu_check_affinity(struct irq_data *d, const struct cpumask *dest)
                 return -EINVAL;
 
         /* whatever mask they set, we just allow one CPU */
-        cpu_dest = first_cpu(*dest);
+        cpu_dest = cpumask_first_and(dest, cpu_online_mask);
 
         return cpu_dest;
 }
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 8fa3fbb3e4d3..80e5dd248934 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -431,6 +431,7 @@
         ENTRY_SAME(finit_module)
         ENTRY_SAME(sched_setattr)
         ENTRY_SAME(sched_getattr)       /* 335 */
+        ENTRY_COMP(utimes)
 
         /* Nothing yet */
 
diff --git a/arch/powerpc/include/asm/Kbuild b/arch/powerpc/include/asm/Kbuild
index 6c0a955a1b06..3fb1bc432f4f 100644
--- a/arch/powerpc/include/asm/Kbuild
+++ b/arch/powerpc/include/asm/Kbuild
@@ -1,7 +1,8 @@
 
 generic-y += clkdev.h
+generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
 generic-y += rwsem.h
 generic-y += trace_clock.h
-generic-y += preempt.h
 generic-y += vtime.h
-generic-y += hash.h
diff --git a/arch/powerpc/include/asm/compat.h b/arch/powerpc/include/asm/compat.h
index 84fdf6857c31..a613d2c82fd9 100644
--- a/arch/powerpc/include/asm/compat.h
+++ b/arch/powerpc/include/asm/compat.h
@@ -200,10 +200,11 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 
         /*
          * We can't access below the stack pointer in the 32bit ABI and
-         * can access 288 bytes in the 64bit ABI
+         * can access 288 bytes in the 64bit big-endian ABI,
+         * or 512 bytes with the new ELFv2 little-endian ABI.
          */
         if (!is_32bit_task())
-                usp -= 288;
+                usp -= USER_REDZONE_SIZE;
 
         return (void __user *) (usp - len);
 }
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 40157e2ca691..ed82142a3251 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -816,8 +816,8 @@ int64_t opal_pci_next_error(uint64_t phb_id, uint64_t *first_frozen_pe,
 int64_t opal_pci_poll(uint64_t phb_id);
 int64_t opal_return_cpu(void);
 
-int64_t opal_xscom_read(uint32_t gcid, uint32_t pcb_addr, __be64 *val);
-int64_t opal_xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val);
+int64_t opal_xscom_read(uint32_t gcid, uint64_t pcb_addr, __be64 *val);
+int64_t opal_xscom_write(uint32_t gcid, uint64_t pcb_addr, uint64_t val);
 
 int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
                        uint32_t addr, uint32_t data, uint32_t sz);
diff --git a/arch/powerpc/include/asm/ptrace.h b/arch/powerpc/include/asm/ptrace.h
index becc08e6a65c..279b80f3bb29 100644
--- a/arch/powerpc/include/asm/ptrace.h
+++ b/arch/powerpc/include/asm/ptrace.h
@@ -28,11 +28,23 @@
 
 #ifdef __powerpc64__
 
+/*
+ * Size of redzone that userspace is allowed to use below the stack
+ * pointer.  This is 288 in the 64-bit big-endian ELF ABI, and 512 in
+ * the new ELFv2 little-endian ABI, so we allow the larger amount.
+ *
+ * For kernel code we allow a 288-byte redzone, in order to conserve
+ * kernel stack space; gcc currently only uses 288 bytes, and will
+ * hopefully allow explicit control of the redzone size in future.
+ */
+#define USER_REDZONE_SIZE       512
+#define KERNEL_REDZONE_SIZE     288
+
 #define STACK_FRAME_OVERHEAD    112     /* size of minimum stack frame */
 #define STACK_FRAME_LR_SAVE     2       /* Location of LR in stack frame */
 #define STACK_FRAME_REGS_MARKER ASM_CONST(0x7265677368657265)
 #define STACK_INT_FRAME_SIZE    (sizeof(struct pt_regs) + \
-                                        STACK_FRAME_OVERHEAD + 288)
+                                 STACK_FRAME_OVERHEAD + KERNEL_REDZONE_SIZE)
 #define STACK_FRAME_MARKER      12
 
 /* Size of dummy stack frame allocated when calling signal handler. */
@@ -41,6 +53,8 @@
 
 #else /* __powerpc64__ */
 
+#define USER_REDZONE_SIZE       0
+#define KERNEL_REDZONE_SIZE     0
 #define STACK_FRAME_OVERHEAD    16      /* size of minimum stack frame */
 #define STACK_FRAME_LR_SAVE     1       /* Location of LR in stack frame */
 #define STACK_FRAME_REGS_MARKER ASM_CONST(0x72656773)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index d0b5fca6b077..c9202151079f 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -99,7 +99,6 @@ static inline int prrn_is_enabled(void)
 
 #ifdef CONFIG_SMP
 #include <asm/cputable.h>
-#define smt_capable()           (cpu_has_feature(CPU_FTR_SMT))
 
 #ifdef CONFIG_PPC64
 #include <asm/smp.h>
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index 11c1d069d920..7a13f378ca2c 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -98,17 +98,19 @@ ssize_t copy_oldmem_page(unsigned long pfn, char *buf,
                         size_t csize, unsigned long offset, int userbuf)
 {
         void  *vaddr;
+        phys_addr_t paddr;
 
         if (!csize)
                 return 0;
 
         csize = min_t(size_t, csize, PAGE_SIZE);
+        paddr = pfn << PAGE_SHIFT;
 
-        if ((min_low_pfn < pfn) && (pfn < max_pfn)) {
-                vaddr = __va(pfn << PAGE_SHIFT);
+        if (memblock_is_region_memory(paddr, csize)) {
+                vaddr = __va(paddr);
                 csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
         } else {
-                vaddr = __ioremap(pfn << PAGE_SHIFT, PAGE_SIZE, 0);
+                vaddr = __ioremap(paddr, PAGE_SIZE, 0);
                 csize = copy_oldmem_vaddr(vaddr, buf, csize, offset, userbuf);
                 iounmap(vaddr);
         }
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index fdc679d309ec..bb61ca58ca6d 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -143,13 +143,30 @@ static void eeh_disable_irq(struct pci_dev *dev)
 static void eeh_enable_irq(struct pci_dev *dev)
 {
         struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
-        struct irq_desc *desc;
 
         if ((edev->mode) & EEH_DEV_IRQ_DISABLED) {
                 edev->mode &= ~EEH_DEV_IRQ_DISABLED;
-
-                desc = irq_to_desc(dev->irq);
-                if (desc && desc->depth > 0)
+                /*
+                 * FIXME !!!!!
+                 *
+                 * This is just ass backwards. This maze has
+                 * unbalanced irq_enable/disable calls. So instead of
+                 * finding the root cause it works around the warning
+                 * in the irq_enable code by conditionally calling
+                 * into it.
+                 *
+                 * That's just wrong.The warning in the core code is
+                 * there to tell people to fix their assymetries in
+                 * their own code, not by abusing the core information
+                 * to avoid it.
+                 *
+                 * I so wish that the assymetry would be the other way
+                 * round and a few more irq_disable calls render that
+                 * shit unusable forever.
+                 *
+                 *      tglx
+                 */
+                if (irqd_irq_disabled(irq_get_irq_data(dev->irq)))
                         enable_irq(dev->irq);
         }
 }
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 9b27b293a922..b0ded97ee4e1 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -74,6 +74,7 @@ ftrace_modify_code(unsigned long ip, unsigned int old, unsigned int new)
  */
 static int test_24bit_addr(unsigned long ip, unsigned long addr)
 {
+        addr = ppc_function_entry((void *)addr);
 
         /* use the create_branch to verify that this offset can be branched */
         return create_branch((unsigned int *)ip, addr, 0);
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 1d0848bba049..ca1cd7459c4a 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -465,7 +465,6 @@ static inline void check_stack_overflow(void)
 
 void __do_irq(struct pt_regs *regs)
 {
-        struct irq_desc *desc;
         unsigned int irq;
 
         irq_enter();
@@ -487,11 +486,8 @@ void __do_irq(struct pt_regs *regs)
         /* And finally process it */
         if (unlikely(irq == NO_IRQ))
                 __get_cpu_var(irq_stat).spurious_irqs++;
-        else {
-                desc = irq_to_desc(irq);
-                if (likely(desc))
-                        desc->handle_irq(irq, desc);
-        }
+        else
+                generic_handle_irq(irq);
 
         trace_irq_exit(regs);
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 8d4c247f1738..af064d28b365 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1048,6 +1048,15 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
         flush_altivec_to_thread(src);
         flush_vsx_to_thread(src);
         flush_spe_to_thread(src);
+        /*
+         * Flush TM state out so we can copy it.  __switch_to_tm() does this
+         * flush but it removes the checkpointed state from the current CPU and
+         * transitions the CPU out of TM mode.  Hence we need to call
+         * tm_recheckpoint_new_task() (on the same task) to restore the
+         * checkpointed state back and the TM mode.
+         */
+        __switch_to_tm(src);
+        tm_recheckpoint_new_task(src);
 
         *dst = *src;
 
diff --git a/arch/powerpc/kernel/reloc_64.S b/arch/powerpc/kernel/reloc_64.S
index 1482327cfeba..d88736fbece6 100644
--- a/arch/powerpc/kernel/reloc_64.S
+++ b/arch/powerpc/kernel/reloc_64.S
@@ -81,6 +81,7 @@ _GLOBAL(relocate)
 
 6:      blr
 
+.balign 8
 p_dyn:  .llong  __dynamic_start - 0b
 p_rela: .llong  __rela_dyn_start - 0b
 p_st:   .llong  _stext - 0b
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index e35bf773df7a..8d253c29649b 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -65,8 +65,8 @@ struct rt_sigframe {
         struct siginfo __user *pinfo;
         void __user *puc;
         struct siginfo info;
-        /* 64 bit ABI allows for 288 bytes below sp before decrementing it. */
-        char abigap[288];
+        /* New 64 bit little-endian ABI allows redzone of 512 bytes below sp */
+        char abigap[USER_REDZONE_SIZE];
 } __attribute__ ((aligned (16)));
 
 static const char fmt32[] = KERN_INFO \
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e66d4ec04d95..818dce344e82 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1504,73 +1504,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 1:      addi    r8,r8,16
         .endr
 
-        /* Save DEC */
-        mfspr   r5,SPRN_DEC
-        mftb    r6
-        extsw   r5,r5
-        add     r5,r5,r6
-        std     r5,VCPU_DEC_EXPIRES(r9)
-
-BEGIN_FTR_SECTION
-        b       8f
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
-        /* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
-        mfmsr   r8
-        li      r0, 1
-        rldimi  r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-        mtmsrd  r8
-
-        /* Save POWER8-specific registers */
-        mfspr   r5, SPRN_IAMR
-        mfspr   r6, SPRN_PSPB
-        mfspr   r7, SPRN_FSCR
-        std     r5, VCPU_IAMR(r9)
-        stw     r6, VCPU_PSPB(r9)
-        std     r7, VCPU_FSCR(r9)
-        mfspr   r5, SPRN_IC
-        mfspr   r6, SPRN_VTB
-        mfspr   r7, SPRN_TAR
-        std     r5, VCPU_IC(r9)
-        std     r6, VCPU_VTB(r9)
-        std     r7, VCPU_TAR(r9)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-        mfspr   r5, SPRN_TFHAR
-        mfspr   r6, SPRN_TFIAR
-        mfspr   r7, SPRN_TEXASR
-        std     r5, VCPU_TFHAR(r9)
-        std     r6, VCPU_TFIAR(r9)
-        std     r7, VCPU_TEXASR(r9)
-#endif
-        mfspr   r8, SPRN_EBBHR
-        std     r8, VCPU_EBBHR(r9)
-        mfspr   r5, SPRN_EBBRR
-        mfspr   r6, SPRN_BESCR
-        mfspr   r7, SPRN_CSIGR
-        mfspr   r8, SPRN_TACR
-        std     r5, VCPU_EBBRR(r9)
-        std     r6, VCPU_BESCR(r9)
-        std     r7, VCPU_CSIGR(r9)
-        std     r8, VCPU_TACR(r9)
-        mfspr   r5, SPRN_TCSCR
-        mfspr   r6, SPRN_ACOP
-        mfspr   r7, SPRN_PID
-        mfspr   r8, SPRN_WORT
-        std     r5, VCPU_TCSCR(r9)
-        std     r6, VCPU_ACOP(r9)
-        stw     r7, VCPU_GUEST_PID(r9)
-        std     r8, VCPU_WORT(r9)
-8:
-
-        /* Save and reset AMR and UAMOR before turning on the MMU */
-BEGIN_FTR_SECTION
-        mfspr   r5,SPRN_AMR
-        mfspr   r6,SPRN_UAMOR
-        std     r5,VCPU_AMR(r9)
-        std     r6,VCPU_UAMOR(r9)
-        li      r6,0
-        mtspr   SPRN_AMR,r6
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
         /* Unset guest mode */
         li      r0, KVM_GUEST_MODE_NONE
         stb     r0, HSTATE_IN_GUEST(r13)
@@ -2203,7 +2136,7 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
         mfspr   r6,SPRN_VRSAVE
-        stw     r6,VCPU_VRSAVE(r3)
+        stw     r6,VCPU_VRSAVE(r31)
         mtlr    r30
         mtmsrd  r5
         isync
@@ -2240,7 +2173,7 @@ BEGIN_FTR_SECTION
         bl      .load_vr_state
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
-        lwz     r7,VCPU_VRSAVE(r4)
+        lwz     r7,VCPU_VRSAVE(r31)
         mtspr   SPRN_VRSAVE,r7
         mtlr    r30
         mr      r4,r31
diff --git a/arch/powerpc/platforms/cell/ras.c b/arch/powerpc/platforms/cell/ras.c
index 5ec1e47a0d77..e865d748179b 100644
--- a/arch/powerpc/platforms/cell/ras.c
+++ b/arch/powerpc/platforms/cell/ras.c
@@ -123,7 +123,8 @@ static int __init cbe_ptcal_enable_on_node(int nid, int order)
 
         area->nid = nid;
         area->order = order;
-        area->pages = alloc_pages_exact_node(area->nid, GFP_KERNEL|GFP_THISNODE,
+        area->pages = alloc_pages_exact_node(area->nid,
+                                                GFP_KERNEL|__GFP_THISNODE,
                                                 area->order);
 
         if (!area->pages) {
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 49318385d4fa..4a0a64fe25df 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -83,7 +83,6 @@ static struct timer_list spuloadavg_timer;
 #define MIN_SPU_TIMESLICE       max(5 * HZ / (1000 * SPUSCHED_TICK), 1)
 #define DEF_SPU_TIMESLICE       (100 * HZ / (1000 * SPUSCHED_TICK))
 
-#define MAX_USER_PRIO           (MAX_PRIO - MAX_RT_PRIO)
 #define SCALE_PRIO(x, prio) \
         max(x * (MAX_PRIO - prio) / (MAX_USER_PRIO / 2), MIN_SPU_TIMESLICE)
 
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index f51474336460..253fefe3d1a0 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -114,6 +114,7 @@ DEFINE_SIMPLE_ATTRIBUTE(ioda_eeh_inbB_dbgfs_ops, ioda_eeh_inbB_dbgfs_get,
                         ioda_eeh_inbB_dbgfs_set, "0x%llx\n");
 #endif /* CONFIG_DEBUG_FS */
 
+
 /**
  * ioda_eeh_post_init - Chip dependent post initialization
  * @hose: PCI controller
@@ -221,6 +222,22 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
         return ret;
 }
 
+static void ioda_eeh_phb_diag(struct pci_controller *hose)
+{
+        struct pnv_phb *phb = hose->private_data;
+        long rc;
+
+        rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
+                                         PNV_PCI_DIAG_BUF_SIZE);
+        if (rc != OPAL_SUCCESS) {
+                pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
+                            __func__, hose->global_number, rc);
+                return;
+        }
+
+        pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
+}
+
 /**
  * ioda_eeh_get_state - Retrieve the state of PE
  * @pe: EEH PE
@@ -272,6 +289,9 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
                         result |= EEH_STATE_DMA_ACTIVE;
                         result |= EEH_STATE_MMIO_ENABLED;
                         result |= EEH_STATE_DMA_ENABLED;
+                } else if (!(pe->state & EEH_PE_ISOLATED)) {
+                        eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+                        ioda_eeh_phb_diag(hose);
                 }
 
                 return result;
@@ -315,6 +335,15 @@ static int ioda_eeh_get_state(struct eeh_pe *pe)
                            __func__, fstate, hose->global_number, pe_no);
         }
 
+        /* Dump PHB diag-data for frozen PE */
+        if (result != EEH_STATE_NOT_SUPPORT &&
+            (result & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) !=
+            (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE) &&
+            !(pe->state & EEH_PE_ISOLATED)) {
+                eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+                ioda_eeh_phb_diag(hose);
+        }
+
         return result;
 }
 
@@ -530,42 +559,6 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 }
 
 /**
- * ioda_eeh_get_log - Retrieve error log
- * @pe: EEH PE
- * @severity: Severity level of the log
- * @drv_log: buffer to store the log
- * @len: space of the log buffer
- *
- * The function is used to retrieve error log from P7IOC.
- */
-static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
-                            char *drv_log, unsigned long len)
-{
-        s64 ret;
-        unsigned long flags;
-        struct pci_controller *hose = pe->phb;
-        struct pnv_phb *phb = hose->private_data;
-
-        spin_lock_irqsave(&phb->lock, flags);
-
-        ret = opal_pci_get_phb_diag_data2(phb->opal_id,
-                        phb->diag.blob, PNV_PCI_DIAG_BUF_SIZE);
-        if (ret) {
-                spin_unlock_irqrestore(&phb->lock, flags);
-                pr_warning("%s: Can't get log for PHB#%x-PE#%x (%lld)\n",
-                           __func__, hose->global_number, pe->addr, ret);
-                return -EIO;
-        }
-
-        /* The PHB diag-data is always indicative */
-        pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-
-        spin_unlock_irqrestore(&phb->lock, flags);
-
-        return 0;
-}
-
-/**
  * ioda_eeh_configure_bridge - Configure the PCI bridges for the indicated PE
  * @pe: EEH PE
  *
@@ -646,22 +639,6 @@ static void ioda_eeh_hub_diag(struct pci_controller *hose)
         }
 }
 
-static void ioda_eeh_phb_diag(struct pci_controller *hose)
-{
-        struct pnv_phb *phb = hose->private_data;
-        long rc;
-
-        rc = opal_pci_get_phb_diag_data2(phb->opal_id, phb->diag.blob,
-                                         PNV_PCI_DIAG_BUF_SIZE);
-        if (rc != OPAL_SUCCESS) {
-                pr_warning("%s: Failed to get diag-data for PHB#%x (%ld)\n",
-                            __func__, hose->global_number, rc);
-                return;
-        }
-
-        pnv_pci_dump_phb_diag_data(hose, phb->diag.blob);
-}
-
 static int ioda_eeh_get_phb_pe(struct pci_controller *hose,
                                struct eeh_pe **pe)
 {
@@ -835,6 +812,20 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
                 }
 
                 /*
+                 * EEH core will try recover from fenced PHB or
+                 * frozen PE. In the time for frozen PE, EEH core
+                 * enable IO path for that before collecting logs,
+                 * but it ruins the site. So we have to dump the
+                 * log in advance here.
+                 */
+                if ((ret == EEH_NEXT_ERR_FROZEN_PE  ||
+                    ret == EEH_NEXT_ERR_FENCED_PHB) &&
+                    !((*pe)->state & EEH_PE_ISOLATED)) {
+                        eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
+                        ioda_eeh_phb_diag(hose);
+                }
+
+                /*
                  * If we have no errors on the specific PHB or only
                  * informative error there, we continue poking it.
                  * Otherwise, we need actions to be taken by upper
@@ -852,7 +843,6 @@ struct pnv_eeh_ops ioda_eeh_ops = {
         .set_option             = ioda_eeh_set_option,
         .get_state              = ioda_eeh_get_state,
         .reset                  = ioda_eeh_reset,
-        .get_log                = ioda_eeh_get_log,
         .configure_bridge       = ioda_eeh_configure_bridge,
         .next_error             = ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/opal-xscom.c b/arch/powerpc/platforms/powernv/opal-xscom.c
index 4fbf276ac99e..4cd2ea6c0dbe 100644
--- a/arch/powerpc/platforms/powernv/opal-xscom.c
+++ b/arch/powerpc/platforms/powernv/opal-xscom.c
@@ -71,11 +71,11 @@ static int opal_xscom_err_xlate(int64_t rc)
         }
 }
 
-static u64 opal_scom_unmangle(u64 reg)
+static u64 opal_scom_unmangle(u64 addr)
 {
         /*
          * XSCOM indirect addresses have the top bit set. Additionally
-         * the reset of the top 3 nibbles is always 0.
+         * the rest of the top 3 nibbles is always 0.
          *
          * Because the debugfs interface uses signed offsets and shifts
          * the address left by 3, we basically cannot use the top 4 bits
@@ -86,10 +86,13 @@ static u64 opal_scom_unmangle(u64 reg)
          * conversion here. To leave room for further xscom address
          * expansion, we only clear out the top byte
          *
+         * For in-kernel use, we also support the real indirect bit, so
+         * we test for any of the top 5 bits
+         *
          */
-        if (reg & (1ull << 59))
-                reg = (reg & ~(0xffull << 56)) | (1ull << 63);
-        return reg;
+        if (addr & (0x1full << 59))
+                addr = (addr & ~(0xffull << 56)) | (1ull << 63);
+        return addr;
 }
 
 static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
@@ -98,8 +101,8 @@ static int opal_scom_read(scom_map_t map, u64 reg, u64 *value)
         int64_t rc;
         __be64 v;
 
-        reg = opal_scom_unmangle(reg);
-        rc = opal_xscom_read(m->chip, m->addr + reg, (__be64 *)__pa(&v));
+        reg = opal_scom_unmangle(m->addr + reg);
+        rc = opal_xscom_read(m->chip, reg, (__be64 *)__pa(&v));
         *value = be64_to_cpu(v);
         return opal_xscom_err_xlate(rc);
 }
@@ -109,8 +112,8 @@ static int opal_scom_write(scom_map_t map, u64 reg, u64 value)
         struct opal_scom_map *m = map;
         int64_t rc;
 
-        reg = opal_scom_unmangle(reg);
-        rc = opal_xscom_write(m->chip, m->addr + reg, value);
+        reg = opal_scom_unmangle(m->addr + reg);
+        rc = opal_xscom_write(m->chip, reg, value);
         return opal_xscom_err_xlate(rc);
 }
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 95633d79ef5d..8518817dcdfd 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -134,57 +134,72 @@ static void pnv_pci_dump_p7ioc_diag_data(struct pci_controller *hose,
         pr_info("P7IOC PHB#%d Diag-data (Version: %d)\n\n",
                 hose->global_number, common->version);
 
-        pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-        pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-        pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-        pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-        pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-        pr_info("  slotStatus:           %08x\n", data->slotStatus);
-        pr_info("  linkStatus:           %08x\n", data->linkStatus);
-        pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-        pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-        pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-        pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-        pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-        pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-        pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-        pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-        pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-        pr_info("  sourceId:             %08x\n", data->sourceId);
-        pr_info("  errorClass:           %016llx\n", data->errorClass);
-        pr_info("  correlator:           %016llx\n", data->correlator);
-        pr_info("  p7iocPlssr:           %016llx\n", data->p7iocPlssr);
-        pr_info("  p7iocCsr:             %016llx\n", data->p7iocCsr);
-        pr_info("  lemFir:               %016llx\n", data->lemFir);
-        pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-        pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-        pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-        pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-        pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-        pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-        pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-        pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-        pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-        pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-        pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-        pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-        pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-        pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-        pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-        pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-        pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-        pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+        if (data->brdgCtl)
+                pr_info("  brdgCtl:     %08x\n",
+                        data->brdgCtl);
+        if (data->portStatusReg || data->rootCmplxStatus ||
+            data->busAgentStatus)
+                pr_info("  UtlSts:      %08x %08x %08x\n",
+                        data->portStatusReg, data->rootCmplxStatus,
+                        data->busAgentStatus);
+        if (data->deviceStatus || data->slotStatus   ||
+            data->linkStatus   || data->devCmdStatus ||
+            data->devSecStatus)
+                pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+                        data->deviceStatus, data->slotStatus,
+                        data->linkStatus, data->devCmdStatus,
+                        data->devSecStatus);
+        if (data->rootErrorStatus   || data->uncorrErrorStatus ||
+            data->corrErrorStatus)
+                pr_info("  RootErrSts:  %08x %08x %08x\n",
+                        data->rootErrorStatus, data->uncorrErrorStatus,
+                        data->corrErrorStatus);
+        if (data->tlpHdr1 || data->tlpHdr2 ||
+            data->tlpHdr3 || data->tlpHdr4)
+                pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+                        data->tlpHdr1, data->tlpHdr2,
+                        data->tlpHdr3, data->tlpHdr4);
+        if (data->sourceId || data->errorClass ||
+            data->correlator)
+                pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+                        data->sourceId, data->errorClass,
+                        data->correlator);
+        if (data->p7iocPlssr || data->p7iocCsr)
+                pr_info("  PhbSts:      %016llx %016llx\n",
+                        data->p7iocPlssr, data->p7iocCsr);
+        if (data->lemFir || data->lemErrorMask ||
+            data->lemWOF)
+                pr_info("  Lem:         %016llx %016llx %016llx\n",
+                        data->lemFir, data->lemErrorMask,
+                        data->lemWOF);
+        if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+            data->phbErrorLog0   || data->phbErrorLog1)
+                pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+                        data->phbErrorStatus, data->phbFirstErrorStatus,
+                        data->phbErrorLog0, data->phbErrorLog1);
+        if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+            data->mmioErrorLog0   || data->mmioErrorLog1)
+                pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+                        data->mmioErrorStatus, data->mmioFirstErrorStatus,
+                        data->mmioErrorLog0, data->mmioErrorLog1);
+        if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+            data->dma0ErrorLog0   || data->dma0ErrorLog1)
+                pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+                        data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+                        data->dma0ErrorLog0, data->dma0ErrorLog1);
+        if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+            data->dma1ErrorLog0   || data->dma1ErrorLog1)
+                pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+                        data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+                        data->dma1ErrorLog0, data->dma1ErrorLog1);
 
         for (i = 0; i < OPAL_P7IOC_NUM_PEST_REGS; i++) {
                 if ((data->pestA[i] >> 63) == 0 &&
                     (data->pestB[i] >> 63) == 0)
                         continue;
 
-                pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-                pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+                pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+                        i, data->pestA[i], data->pestB[i]);
         }
 }
 
@@ -197,62 +212,77 @@ static void pnv_pci_dump_phb3_diag_data(struct pci_controller *hose,
         data = (struct OpalIoPhb3ErrorData*)common;
         pr_info("PHB3 PHB#%d Diag-data (Version: %d)\n\n",
                 hose->global_number, common->version);
-
-        pr_info("  brdgCtl:              %08x\n", data->brdgCtl);
-
-        pr_info("  portStatusReg:        %08x\n", data->portStatusReg);
-        pr_info("  rootCmplxStatus:      %08x\n", data->rootCmplxStatus);
-        pr_info("  busAgentStatus:       %08x\n", data->busAgentStatus);
-
-        pr_info("  deviceStatus:         %08x\n", data->deviceStatus);
-        pr_info("  slotStatus:           %08x\n", data->slotStatus);
-        pr_info("  linkStatus:           %08x\n", data->linkStatus);
-        pr_info("  devCmdStatus:         %08x\n", data->devCmdStatus);
-        pr_info("  devSecStatus:         %08x\n", data->devSecStatus);
-
-        pr_info("  rootErrorStatus:      %08x\n", data->rootErrorStatus);
-        pr_info("  uncorrErrorStatus:    %08x\n", data->uncorrErrorStatus);
-        pr_info("  corrErrorStatus:      %08x\n", data->corrErrorStatus);
-        pr_info("  tlpHdr1:              %08x\n", data->tlpHdr1);
-        pr_info("  tlpHdr2:              %08x\n", data->tlpHdr2);
-        pr_info("  tlpHdr3:              %08x\n", data->tlpHdr3);
-        pr_info("  tlpHdr4:              %08x\n", data->tlpHdr4);
-        pr_info("  sourceId:             %08x\n", data->sourceId);
-        pr_info("  errorClass:           %016llx\n", data->errorClass);
-        pr_info("  correlator:           %016llx\n", data->correlator);
-
-        pr_info("  nFir:                 %016llx\n", data->nFir);
-        pr_info("  nFirMask:             %016llx\n", data->nFirMask);
-        pr_info("  nFirWOF:              %016llx\n", data->nFirWOF);
-        pr_info("  PhbPlssr:             %016llx\n", data->phbPlssr);
-        pr_info("  PhbCsr:               %016llx\n", data->phbCsr);
-        pr_info("  lemFir:               %016llx\n", data->lemFir);
-        pr_info("  lemErrorMask:         %016llx\n", data->lemErrorMask);
-        pr_info("  lemWOF:               %016llx\n", data->lemWOF);
-        pr_info("  phbErrorStatus:       %016llx\n", data->phbErrorStatus);
-        pr_info("  phbFirstErrorStatus:  %016llx\n", data->phbFirstErrorStatus);
-        pr_info("  phbErrorLog0:         %016llx\n", data->phbErrorLog0);
-        pr_info("  phbErrorLog1:         %016llx\n", data->phbErrorLog1);
-        pr_info("  mmioErrorStatus:      %016llx\n", data->mmioErrorStatus);
-        pr_info("  mmioFirstErrorStatus: %016llx\n", data->mmioFirstErrorStatus);
-        pr_info("  mmioErrorLog0:        %016llx\n", data->mmioErrorLog0);
-        pr_info("  mmioErrorLog1:        %016llx\n", data->mmioErrorLog1);
-        pr_info("  dma0ErrorStatus:      %016llx\n", data->dma0ErrorStatus);
-        pr_info("  dma0FirstErrorStatus: %016llx\n", data->dma0FirstErrorStatus);
-        pr_info("  dma0ErrorLog0:        %016llx\n", data->dma0ErrorLog0);
-        pr_info("  dma0ErrorLog1:        %016llx\n", data->dma0ErrorLog1);
-        pr_info("  dma1ErrorStatus:      %016llx\n", data->dma1ErrorStatus);
-        pr_info("  dma1FirstErrorStatus: %016llx\n", data->dma1FirstErrorStatus);
-        pr_info("  dma1ErrorLog0:        %016llx\n", data->dma1ErrorLog0);
-        pr_info("  dma1ErrorLog1:        %016llx\n", data->dma1ErrorLog1);
+        if (data->brdgCtl)
+                pr_info("  brdgCtl:     %08x\n",
+                        data->brdgCtl);
+        if (data->portStatusReg || data->rootCmplxStatus ||
+            data->busAgentStatus)
+                pr_info("  UtlSts:      %08x %08x %08x\n",
+                        data->portStatusReg, data->rootCmplxStatus,
+                        data->busAgentStatus);
+        if (data->deviceStatus || data->slotStatus   ||
+            data->linkStatus   || data->devCmdStatus ||
+            data->devSecStatus)
+                pr_info("  RootSts:     %08x %08x %08x %08x %08x\n",
+                        data->deviceStatus, data->slotStatus,
+                        data->linkStatus, data->devCmdStatus,
+                        data->devSecStatus);
+        if (data->rootErrorStatus || data->uncorrErrorStatus ||
+            data->corrErrorStatus)
+                pr_info("  RootErrSts:  %08x %08x %08x\n",
+                        data->rootErrorStatus, data->uncorrErrorStatus,
+                        data->corrErrorStatus);
+        if (data->tlpHdr1 || data->tlpHdr2 ||
+            data->tlpHdr3 || data->tlpHdr4)
+                pr_info("  RootErrLog:  %08x %08x %08x %08x\n",
+                        data->tlpHdr1, data->tlpHdr2,
+                        data->tlpHdr3, data->tlpHdr4);
+        if (data->sourceId || data->errorClass ||
+            data->correlator)
+                pr_info("  RootErrLog1: %08x %016llx %016llx\n",
+                        data->sourceId, data->errorClass,
+                        data->correlator);
+        if (data->nFir || data->nFirMask ||
+            data->nFirWOF)
+                pr_info("  nFir:        %016llx %016llx %016llx\n",
+                        data->nFir, data->nFirMask,
+                        data->nFirWOF);
+        if (data->phbPlssr || data->phbCsr)
+                pr_info("  PhbSts:      %016llx %016llx\n",
+                        data->phbPlssr, data->phbCsr);
+        if (data->lemFir || data->lemErrorMask ||
+            data->lemWOF)
+                pr_info("  Lem:         %016llx %016llx %016llx\n",
+                        data->lemFir, data->lemErrorMask,
+                        data->lemWOF);
+        if (data->phbErrorStatus || data->phbFirstErrorStatus ||
+            data->phbErrorLog0   || data->phbErrorLog1)
+                pr_info("  PhbErr:      %016llx %016llx %016llx %016llx\n",
+                        data->phbErrorStatus, data->phbFirstErrorStatus,
+                        data->phbErrorLog0, data->phbErrorLog1);
+        if (data->mmioErrorStatus || data->mmioFirstErrorStatus ||
+            data->mmioErrorLog0   || data->mmioErrorLog1)
+                pr_info("  OutErr:      %016llx %016llx %016llx %016llx\n",
+                        data->mmioErrorStatus, data->mmioFirstErrorStatus,
+                        data->mmioErrorLog0, data->mmioErrorLog1);
+        if (data->dma0ErrorStatus || data->dma0FirstErrorStatus ||
+            data->dma0ErrorLog0   || data->dma0ErrorLog1)
+                pr_info("  InAErr:      %016llx %016llx %016llx %016llx\n",
+                        data->dma0ErrorStatus, data->dma0FirstErrorStatus,
+                        data->dma0ErrorLog0, data->dma0ErrorLog1);
+        if (data->dma1ErrorStatus || data->dma1FirstErrorStatus ||
+            data->dma1ErrorLog0   || data->dma1ErrorLog1)
+                pr_info("  InBErr:      %016llx %016llx %016llx %016llx\n",
+                        data->dma1ErrorStatus, data->dma1FirstErrorStatus,
+                        data->dma1ErrorLog0, data->dma1ErrorLog1);
 
         for (i = 0; i < OPAL_PHB3_NUM_PEST_REGS; i++) {
                 if ((data->pestA[i] >> 63) == 0 &&
                     (data->pestB[i] >> 63) == 0)
                         continue;
 
-                pr_info("  PE[%3d] PESTA:        %016llx\n", i, data->pestA[i]);
-                pr_info("          PESTB:        %016llx\n", data->pestB[i]);
+                pr_info("  PE[%3d] A/B: %016llx %016llx\n",
+                        i, data->pestA[i], data->pestB[i]);
         }
 }
 
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 110f4fbd319f..81a7a0a79be7 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -26,7 +26,6 @@
 #include <linux/of_fdt.h>
 #include <linux/interrupt.h>
 #include <linux/bug.h>
-#include <linux/cpuidle.h>
 #include <linux/pci.h>
 
 #include <asm/machdep.h>
@@ -225,16 +224,6 @@ static int __init pnv_probe(void)
         return 1;
 }
 
-void powernv_idle(void)
-{
-        /* Hook to cpuidle framework if available, else
-         * call on default platform idle code
-         */
-        if (cpuidle_idle_call()) {
-                power7_idle();
-        }
-}
-
 define_machine(powernv) {
         .name                   = "PowerNV",
         .probe                  = pnv_probe,
@@ -244,7 +233,7 @@ define_machine(powernv) {
         .show_cpuinfo           = pnv_show_cpuinfo,
         .progress               = pnv_progress,
         .machine_shutdown       = pnv_shutdown,
-        .power_save             = powernv_idle,
+        .power_save             = power7_idle,
         .calibrate_decr         = generic_calibrate_decr,
         .dma_set_mask           = pnv_dma_set_mask,
 #ifdef CONFIG_KEXEC
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 82789e79e539..0ea99e3d4815 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -35,12 +35,7 @@
 #include "offline_states.h"
 
 /* This version can't take the spinlock, because it never returns */
-static struct rtas_args rtas_stop_self_args = {
-        .token = RTAS_UNKNOWN_SERVICE,
-        .nargs = 0,
-        .nret = 1,
-        .rets = &rtas_stop_self_args.args[0],
-};
+static int rtas_stop_self_token = RTAS_UNKNOWN_SERVICE;
 
 static DEFINE_PER_CPU(enum cpu_state_vals, preferred_offline_state) =
                                                         CPU_STATE_OFFLINE;
@@ -93,15 +88,20 @@ void set_default_offline_state(int cpu)
 
 static void rtas_stop_self(void)
 {
-        struct rtas_args *args = &rtas_stop_self_args;
+        struct rtas_args args = {
+                .token = cpu_to_be32(rtas_stop_self_token),
+                .nargs = 0,
+                .nret = 1,
+                .rets = &args.args[0],
+        };
 
         local_irq_disable();
 
-        BUG_ON(args->token == RTAS_UNKNOWN_SERVICE);
+        BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
 
         printk("cpu %u (hwid %u) Ready to die...\n",
                smp_processor_id(), hard_smp_processor_id());
-        enter_rtas(__pa(args));
+        enter_rtas(__pa(&args));
 
         panic("Alas, I survived.\n");
 }
@@ -392,10 +392,10 @@ static int __init pseries_cpu_hotplug_init(void)
                 }
         }
 
-        rtas_stop_self_args.token = rtas_token("stop-self");
+        rtas_stop_self_token = rtas_token("stop-self");
         qcss_tok = rtas_token("query-cpu-stopped-state");
 
-        if (rtas_stop_self_args.token == RTAS_UNKNOWN_SERVICE ||
+        if (rtas_stop_self_token == RTAS_UNKNOWN_SERVICE ||
                         qcss_tok == RTAS_UNKNOWN_SERVICE) {
                 printk(KERN_INFO "CPU Hotplug not supported by firmware "
                                 "- disabling.\n");
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 972df0ffd4dc..2db8cc691bf4 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -39,7 +39,6 @@
 #include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
-#include <linux/cpuidle.h>
 #include <linux/of.h>
 #include <linux/kexec.h>
 
@@ -356,29 +355,24 @@ early_initcall(alloc_dispatch_log_kmem_cache);
 
 static void pseries_lpar_idle(void)
 {
-        /* This would call on the cpuidle framework, and the back-end pseries
-         * driver to  go to idle states
+        /*
+         * Default handler to go into low thread priority and possibly
+         * low power mode by cedeing processor to hypervisor
          */
-        if (cpuidle_idle_call()) {
-                /* On error, execute default handler
-                 * to go into low thread priority and possibly
-                 * low power mode by cedeing processor to hypervisor
-                 */
 
-                /* Indicate to hypervisor that we are idle. */
-                get_lppaca()->idle = 1;
+        /* Indicate to hypervisor that we are idle. */
+        get_lppaca()->idle = 1;
 
-                /*
-                 * Yield the processor to the hypervisor.  We return if
-                 * an external interrupt occurs (which are driven prior
-                 * to returning here) or if a prod occurs from another
-                 * processor. When returning here, external interrupts
-                 * are enabled.
-                 */
-                cede_processor();
+        /*
+         * Yield the processor to the hypervisor.  We return if
+         * an external interrupt occurs (which are driven prior
+         * to returning here) or if a prod occurs from another
+         * processor. When returning here, external interrupts
+         * are enabled.
+         */
+        cede_processor();
 
-                get_lppaca()->idle = 0;
-        }
+        get_lppaca()->idle = 0;
 }
 
 /*
diff --git a/arch/powerpc/sysdev/ehv_pic.c b/arch/powerpc/sysdev/ehv_pic.c
index b74085cea1af..2d20f10a4203 100644
--- a/arch/powerpc/sysdev/ehv_pic.c
+++ b/arch/powerpc/sysdev/ehv_pic.c
@@ -28,8 +28,6 @@
 #include <asm/ehv_pic.h>
 #include <asm/fsl_hcalls.h>
 
-#include "../../../kernel/irq/settings.h"
-
 static struct ehv_pic *global_ehv_pic;
 static DEFINE_SPINLOCK(ehv_pic_lock);
 
@@ -113,17 +111,13 @@ static unsigned int ehv_pic_type_to_vecpri(unsigned int type)
 int ehv_pic_set_irq_type(struct irq_data *d, unsigned int flow_type)
 {
         unsigned int src = virq_to_hw(d->irq);
-        struct irq_desc *desc = irq_to_desc(d->irq);
         unsigned int vecpri, vold, vnew, prio, cpu_dest;
         unsigned long flags;
 
         if (flow_type == IRQ_TYPE_NONE)
                 flow_type = IRQ_TYPE_LEVEL_LOW;
 
-        irq_settings_clr_level(desc);
-        irq_settings_set_trigger_mask(desc, flow_type);
-        if (flow_type & (IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_LEVEL_LOW))
-                irq_settings_set_level(desc);
+        irqd_set_trigger_type(d, flow_type);
 
         vecpri = ehv_pic_type_to_vecpri(flow_type);
 
@@ -144,7 +138,7 @@ int ehv_pic_set_irq_type(struct irq_data *d, unsigned int flow_type)
         ev_int_set_config(src, vecpri, prio, cpu_dest);
 
         spin_unlock_irqrestore(&ehv_pic_lock, flags);
-        return 0;
+        return IRQ_SET_MASK_OK_NOCOPY;
 }
 
 static struct irq_chip ehv_pic_irq_chip = {
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 65a07750f4f9..953f17c8d17c 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -117,6 +117,7 @@ config S390
         select HAVE_FUNCTION_GRAPH_TRACER
         select HAVE_FUNCTION_TRACER
         select HAVE_FUNCTION_TRACE_MCOUNT_TEST
+        select HAVE_FUTEX_CMPXCHG if FUTEX
         select HAVE_KERNEL_BZIP2
         select HAVE_KERNEL_GZIP
         select HAVE_KERNEL_LZ4
@@ -140,6 +141,7 @@ config S390
         select OLD_SIGACTION
         select OLD_SIGSUSPEND3
         select SYSCTL_EXCEPTION_TRACE
+        select TTY
         select VIRT_CPU_ACCOUNTING
         select VIRT_TO_BUS
 
@@ -415,6 +417,10 @@ config ARCH_ENABLE_MEMORY_HOTPLUG
 config ARCH_ENABLE_MEMORY_HOTREMOVE
         def_bool y
 
+config ARCH_ENABLE_SPLIT_PMD_PTLOCK
+        def_bool y
+        depends on 64BIT
+
 config FORCE_MAX_ZONEORDER
         int
         default "9"
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index de8e2b3b0180..69b23b25ac34 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -171,7 +171,7 @@ static int __init appldata_os_init(void)
         int rc, max_size;
 
         max_size = sizeof(struct appldata_os_data) +
-                   (NR_CPUS * sizeof(struct appldata_os_per_cpu));
+                   (num_possible_cpus() * sizeof(struct appldata_os_per_cpu));
         if (max_size > APPLDATA_MAX_REC_SIZE) {
                 pr_err("Maximum OS record size %i exceeds the maximum "
                        "record size %i\n", max_size, APPLDATA_MAX_REC_SIZE);
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index e0af2ee58751..ddaae2f5c913 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -46,6 +46,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z9_109=y
+CONFIG_NR_CPUS=256
 CONFIG_PREEMPT=y
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
@@ -58,7 +59,6 @@ CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-CONFIG_ZFCPDUMP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
@@ -101,7 +101,6 @@ CONFIG_TCP_CONG_VENO=m
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
 CONFIG_IPV6=y
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -111,6 +110,7 @@ CONFIG_INET6_XFRM_MODE_TRANSPORT=m
 CONFIG_INET6_XFRM_MODE_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_BEET=m
 CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_SIT=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
@@ -135,7 +135,17 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
-CONFIG_NETFILTER_TPROXY=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -204,7 +214,9 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
@@ -227,6 +239,11 @@ CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -249,6 +266,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -268,6 +288,7 @@ CONFIG_IP6_NF_SECURITY=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_NET_SCTPPROBE=m
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
@@ -314,6 +335,7 @@ CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
+CONFIG_NET_CLS_BPF=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -381,8 +403,8 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
-CONFIG_DM_RAID=m
 CONFIG_DM_LOG_USERSPACE=m
+CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
@@ -434,7 +456,6 @@ CONFIG_TN3270_FS=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
-CONFIG_ZVM_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
@@ -534,13 +555,23 @@ CONFIG_UNUSED_SYMBOLS=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_DEBUG_OBJECTS=y
+CONFIG_DEBUG_OBJECTS_SELFTEST=y
+CONFIG_DEBUG_OBJECTS_FREE=y
+CONFIG_DEBUG_OBJECTS_TIMERS=y
+CONFIG_DEBUG_OBJECTS_WORK=y
+CONFIG_DEBUG_OBJECTS_RCU_HEAD=y
+CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER=y
 CONFIG_SLUB_DEBUG_ON=y
 CONFIG_SLUB_STATS=y
+CONFIG_DEBUG_KMEMLEAK=y
 CONFIG_DEBUG_STACK_USAGE=y
 CONFIG_DEBUG_VM=y
 CONFIG_DEBUG_VM_RB=y
 CONFIG_MEMORY_NOTIFIER_ERROR_INJECT=m
 CONFIG_DEBUG_PER_CPU_MAPS=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_DETECT_HUNG_TASK=y
 CONFIG_TIMER_STATS=y
 CONFIG_DEBUG_RT_MUTEXES=y
 CONFIG_RT_MUTEX_TESTER=y
@@ -573,9 +604,11 @@ CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_KPROBE_EVENT is not set
 CONFIG_LKDTM=m
+CONFIG_TEST_LIST_SORT=y
 CONFIG_KPROBES_SANITY_TEST=y
-CONFIG_RBTREE_TEST=m
+CONFIG_RBTREE_TEST=y
 CONFIG_INTERVAL_TREE_TEST=m
+CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 CONFIG_DMA_API_DEBUG=y
 # CONFIG_STRICT_DEVMEM is not set
@@ -638,7 +671,6 @@ CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=m
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_PUBLIC_KEY_ALGO_RSA=m
 CONFIG_X509_CERTIFICATE_PARSER=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index b9f6b4cab927..c81a74e3e25a 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -46,6 +46,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z9_109=y
+CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
@@ -56,7 +57,6 @@ CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-CONFIG_ZFCPDUMP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
@@ -99,7 +99,6 @@ CONFIG_TCP_CONG_VENO=m
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
 CONFIG_IPV6=y
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -109,6 +108,7 @@ CONFIG_INET6_XFRM_MODE_TRANSPORT=m
 CONFIG_INET6_XFRM_MODE_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_BEET=m
 CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_SIT=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
@@ -133,7 +133,17 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
-CONFIG_NETFILTER_TPROXY=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -202,7 +212,9 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
@@ -225,6 +237,11 @@ CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -247,6 +264,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -266,6 +286,7 @@ CONFIG_IP6_NF_SECURITY=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_NET_SCTPPROBE=m
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
@@ -311,6 +332,7 @@ CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
+CONFIG_NET_CLS_BPF=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -378,8 +400,8 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
-CONFIG_DM_RAID=m
 CONFIG_DM_LOG_USERSPACE=m
+CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
@@ -431,7 +453,6 @@ CONFIG_TN3270_FS=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
-CONFIG_ZVM_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
@@ -540,6 +561,7 @@ CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_LKDTM=m
 CONFIG_RBTREE_TEST=m
 CONFIG_INTERVAL_TREE_TEST=m
+CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 # CONFIG_STRICT_DEVMEM is not set
 CONFIG_S390_PTDUMP=y
@@ -601,7 +623,6 @@ CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=m
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_PUBLIC_KEY_ALGO_RSA=m
 CONFIG_X509_CERTIFICATE_PARSER=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 91087b43e8fa..b5ba8fe1cc64 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -44,6 +44,7 @@ CONFIG_UNIXWARE_DISKLABEL=y
 CONFIG_CFQ_GROUP_IOSCHED=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z9_109=y
+CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
@@ -54,7 +55,6 @@ CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_S390=y
 CONFIG_CHSC_SCH=y
 CONFIG_CRASH_DUMP=y
-CONFIG_ZFCPDUMP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_BINFMT_MISC=m
 CONFIG_HIBERNATION=y
@@ -97,7 +97,6 @@ CONFIG_TCP_CONG_VENO=m
 CONFIG_TCP_CONG_YEAH=m
 CONFIG_TCP_CONG_ILLINOIS=m
 CONFIG_IPV6=y
-CONFIG_IPV6_PRIVACY=y
 CONFIG_IPV6_ROUTER_PREF=y
 CONFIG_INET6_AH=m
 CONFIG_INET6_ESP=m
@@ -107,6 +106,7 @@ CONFIG_INET6_XFRM_MODE_TRANSPORT=m
 CONFIG_INET6_XFRM_MODE_TUNNEL=m
 CONFIG_INET6_XFRM_MODE_BEET=m
 CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION=m
+CONFIG_IPV6_VTI=m
 CONFIG_IPV6_SIT=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
@@ -131,7 +131,17 @@ CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CT_NETLINK_TIMEOUT=m
-CONFIG_NETFILTER_TPROXY=m
+CONFIG_NF_TABLES=m
+CONFIG_NFT_EXTHDR=m
+CONFIG_NFT_META=m
+CONFIG_NFT_CT=m
+CONFIG_NFT_RBTREE=m
+CONFIG_NFT_HASH=m
+CONFIG_NFT_COUNTER=m
+CONFIG_NFT_LOG=m
+CONFIG_NFT_LIMIT=m
+CONFIG_NFT_NAT=m
+CONFIG_NFT_COMPAT=m
 CONFIG_NETFILTER_XT_SET=m
 CONFIG_NETFILTER_XT_TARGET_AUDIT=m
 CONFIG_NETFILTER_XT_TARGET_CHECKSUM=m
@@ -200,7 +210,9 @@ CONFIG_IP_SET_HASH_IP=m
 CONFIG_IP_SET_HASH_IPPORT=m
 CONFIG_IP_SET_HASH_IPPORTIP=m
 CONFIG_IP_SET_HASH_IPPORTNET=m
+CONFIG_IP_SET_HASH_NETPORTNET=m
 CONFIG_IP_SET_HASH_NET=m
+CONFIG_IP_SET_HASH_NETNET=m
 CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
@@ -223,6 +235,11 @@ CONFIG_IP_VS_FTP=m
 CONFIG_IP_VS_PE_SIP=m
 CONFIG_NF_CONNTRACK_IPV4=m
 # CONFIG_NF_CONNTRACK_PROC_COMPAT is not set
+CONFIG_NF_TABLES_IPV4=m
+CONFIG_NFT_REJECT_IPV4=m
+CONFIG_NFT_CHAIN_ROUTE_IPV4=m
+CONFIG_NFT_CHAIN_NAT_IPV4=m
+CONFIG_NF_TABLES_ARP=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP_NF_MATCH_AH=m
 CONFIG_IP_NF_MATCH_ECN=m
@@ -245,6 +262,9 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
+CONFIG_NF_TABLES_IPV6=m
+CONFIG_NFT_CHAIN_ROUTE_IPV6=m
+CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP6_NF_MATCH_AH=m
 CONFIG_IP6_NF_MATCH_EUI64=m
@@ -264,6 +284,7 @@ CONFIG_IP6_NF_SECURITY=m
 CONFIG_NF_NAT_IPV6=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
+CONFIG_NF_TABLES_BRIDGE=m
 CONFIG_NET_SCTPPROBE=m
 CONFIG_RDS=m
 CONFIG_RDS_RDMA=m
@@ -309,6 +330,7 @@ CONFIG_NET_CLS_RSVP=m
 CONFIG_NET_CLS_RSVP6=m
 CONFIG_NET_CLS_FLOW=m
 CONFIG_NET_CLS_CGROUP=y
+CONFIG_NET_CLS_BPF=m
 CONFIG_NET_CLS_ACT=y
 CONFIG_NET_ACT_POLICE=m
 CONFIG_NET_ACT_GACT=m
@@ -376,8 +398,8 @@ CONFIG_BLK_DEV_DM=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
-CONFIG_DM_RAID=m
 CONFIG_DM_LOG_USERSPACE=m
+CONFIG_DM_RAID=m
 CONFIG_DM_ZERO=m
 CONFIG_DM_MULTIPATH=m
 CONFIG_DM_MULTIPATH_QL=m
@@ -429,7 +451,6 @@ CONFIG_TN3270_FS=y
 CONFIG_WATCHDOG=y
 CONFIG_WATCHDOG_NOWAYOUT=y
 CONFIG_SOFT_WATCHDOG=m
-CONFIG_ZVM_WATCHDOG=m
 # CONFIG_HID is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_INFINIBAND=m
@@ -532,6 +553,7 @@ CONFIG_LATENCYTOP=y
 CONFIG_BLK_DEV_IO_TRACE=y
 # CONFIG_KPROBE_EVENT is not set
 CONFIG_LKDTM=m
+CONFIG_PERCPU_TEST=m
 CONFIG_ATOMIC64_SELFTEST=y
 # CONFIG_STRICT_DEVMEM is not set
 CONFIG_S390_PTDUMP=y
@@ -593,7 +615,6 @@ CONFIG_CRYPTO_AES_S390=m
 CONFIG_CRYPTO_GHASH_S390=m
 CONFIG_ASYMMETRIC_KEY_TYPE=m
 CONFIG_ASYMMETRIC_PUBLIC_KEY_SUBTYPE=m
-CONFIG_PUBLIC_KEY_ALGO_RSA=m
 CONFIG_X509_CERTIFICATE_PARSER=m
 CONFIG_CRC7=m
 CONFIG_CRC8=m
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index d725c4d956e4..cef073ca1f07 100644
--- a/arch/s390/configs/zfcpdump_defconfig
+++ b/arch/s390/configs/zfcpdump_defconfig
@@ -19,7 +19,6 @@ CONFIG_HZ_100=y
 # CONFIG_CHSC_SCH is not set
 # CONFIG_SCM_BUS is not set
 CONFIG_CRASH_DUMP=y
-CONFIG_ZFCPDUMP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_SECCOMP is not set
 # CONFIG_IUCV is not set
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 33f57514f424..4557cb7ffddf 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -40,6 +40,7 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
 CONFIG_MARCH_Z196=y
+CONFIG_NR_CPUS=256
 CONFIG_HZ_100=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
@@ -122,22 +123,31 @@ CONFIG_TMPFS=y
 CONFIG_TMPFS_POSIX_ACL=y
 CONFIG_HUGETLBFS=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
+CONFIG_UNUSED_SYMBOLS=y
+CONFIG_DEBUG_SECTION_MISMATCH=y
 CONFIG_DEBUG_FORCE_WEAK_PER_CPU=y
 CONFIG_MAGIC_SYSRQ=y
 CONFIG_DEBUG_PAGEALLOC=y
+CONFIG_DETECT_HUNG_TASK=y
 CONFIG_TIMER_STATS=y
+CONFIG_DEBUG_RT_MUTEXES=y
 CONFIG_PROVE_LOCKING=y
 CONFIG_LOCK_STAT=y
 CONFIG_DEBUG_LOCKDEP=y
+CONFIG_DEBUG_ATOMIC_SLEEP=y
+CONFIG_DEBUG_WRITECOUNT=y
 CONFIG_DEBUG_LIST=y
+CONFIG_DEBUG_SG=y
 CONFIG_DEBUG_NOTIFIERS=y
 CONFIG_PROVE_RCU=y
 CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_RCU_TRACE=y
 CONFIG_LATENCYTOP=y
+CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y
 CONFIG_BLK_DEV_IO_TRACE=y
 CONFIG_KPROBES_SANITY_TEST=y
 # CONFIG_STRICT_DEVMEM is not set
+CONFIG_S390_PTDUMP=y
 CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_AUTHENC=m
 CONFIG_CRYPTO_TEST=m
diff --git a/arch/s390/hypfs/hypfs_vm.c b/arch/s390/hypfs/hypfs_vm.c
index 24908ce149f1..32040ace00ea 100644
--- a/arch/s390/hypfs/hypfs_vm.c
+++ b/arch/s390/hypfs/hypfs_vm.c
@@ -32,7 +32,7 @@ struct diag2fc_data {
         __u32 pcpus;
         __u32 lcpus;
         __u32 vcpus;
-        __u32 cpu_min;
+        __u32 ocpus;
         __u32 cpu_max;
         __u32 cpu_shares;
         __u32 cpu_use_samp;
@@ -142,7 +142,12 @@ static int hpyfs_vm_create_guest(struct dentry *systems_dir,
         ATTRIBUTE(cpus_dir, "capped", capped_value);
         ATTRIBUTE(cpus_dir, "dedicated", dedicated_flag);
         ATTRIBUTE(cpus_dir, "count", data->vcpus);
-        ATTRIBUTE(cpus_dir, "weight_min", data->cpu_min);
+        /*
+         * Note: The "weight_min" attribute got the wrong name.
+         * The value represents the number of non-stopped (operating)
+         * CPUS.
+         */
+        ATTRIBUTE(cpus_dir, "weight_min", data->ocpus);
         ATTRIBUTE(cpus_dir, "weight_max", data->cpu_max);
         ATTRIBUTE(cpus_dir, "weight_cur", data->cpu_shares);
 
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index 8386a4a1f19a..57892a8a9055 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -1,6 +1,7 @@
 
 
 generic-y += clkdev.h
-generic-y += trace_clock.h
-generic-y += preempt.h
 generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
+generic-y += trace_clock.h
diff --git a/arch/s390/include/asm/airq.h b/arch/s390/include/asm/airq.h
index 4bbb5957ed1b..bd93ff6661b8 100644
--- a/arch/s390/include/asm/airq.h
+++ b/arch/s390/include/asm/airq.h
@@ -44,11 +44,21 @@ struct airq_iv {
 
 struct airq_iv *airq_iv_create(unsigned long bits, unsigned long flags);
 void airq_iv_release(struct airq_iv *iv);
-unsigned long airq_iv_alloc_bit(struct airq_iv *iv);
-void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit);
+unsigned long airq_iv_alloc(struct airq_iv *iv, unsigned long num);
+void airq_iv_free(struct airq_iv *iv, unsigned long bit, unsigned long num);
 unsigned long airq_iv_scan(struct airq_iv *iv, unsigned long start,
                            unsigned long end);
 
+static inline unsigned long airq_iv_alloc_bit(struct airq_iv *iv)
+{
+        return airq_iv_alloc(iv, 1);
+}
+
+static inline void airq_iv_free_bit(struct airq_iv *iv, unsigned long bit)
+{
+        airq_iv_free(iv, bit, 1);
+}
+
 static inline unsigned long airq_iv_end(struct airq_iv *iv)
 {
         return iv->end;
diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h
index 6e6ad0680829..ec5ef891db6b 100644
--- a/arch/s390/include/asm/bitops.h
+++ b/arch/s390/include/asm/bitops.h
@@ -13,9 +13,9 @@
  *
  * The bitop functions are defined to work on unsigned longs, so for an
  * s390x system the bits end up numbered:
- *   |63..............0|127............64|191...........128|255...........196|
+ *   |63..............0|127............64|191...........128|255...........192|
  * and on s390:
- *   |31.....0|63....31|95....64|127...96|159..128|191..160|223..192|255..224|
+ *   |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
  *
  * There are a few little-endian macros used mostly for filesystem
  * bitmaps, these work on similar bit arrays layouts, but
@@ -30,7 +30,7 @@
  * on an s390x system the bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
  * and on s390:
- *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  *
  * The main difference is that bit 0-63 (64b) or 0-31 (32b) in the bit
  * number field needs to be reversed compared to the LSB0 encoded bit
@@ -304,7 +304,7 @@ static inline int test_bit(unsigned long nr, const volatile unsigned long *ptr)
  * On an s390x system the bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
  * and on s390:
- *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  */
 unsigned long find_first_bit_inv(const unsigned long *addr, unsigned long size);
 unsigned long find_next_bit_inv(const unsigned long *addr, unsigned long size,
diff --git a/arch/s390/include/asm/ccwdev.h b/arch/s390/include/asm/ccwdev.h
index f201af8be580..a9c2c0686177 100644
--- a/arch/s390/include/asm/ccwdev.h
+++ b/arch/s390/include/asm/ccwdev.h
@@ -219,7 +219,9 @@ extern void ccw_device_get_id(struct ccw_device *, struct ccw_dev_id *);
 #define to_ccwdev(n) container_of(n, struct ccw_device, dev)
 #define to_ccwdrv(n) container_of(n, struct ccw_driver, driver)
 
-extern struct ccw_device *ccw_device_probe_console(void);
+extern struct ccw_device *ccw_device_create_console(struct ccw_driver *);
+extern void ccw_device_destroy_console(struct ccw_device *);
+extern int ccw_device_enable_console(struct ccw_device *);
 extern void ccw_device_wait_idle(struct ccw_device *);
 extern int ccw_device_force_console(struct ccw_device *);
 
diff --git a/arch/s390/include/asm/checksum.h b/arch/s390/include/asm/checksum.h
index 4f57a4f3909a..740364856355 100644
--- a/arch/s390/include/asm/checksum.h
+++ b/arch/s390/include/asm/checksum.h
@@ -44,22 +44,15 @@ csum_partial(const void *buff, int len, __wsum sum)
  * here even more important to align src and dst on a 32-bit (or even
  * better 64-bit) boundary
  *
- * Copy from userspace and compute checksum.  If we catch an exception
- * then zero the rest of the buffer.
+ * Copy from userspace and compute checksum.
  */
 static inline __wsum
 csum_partial_copy_from_user(const void __user *src, void *dst,
                                           int len, __wsum sum,
                                           int *err_ptr)
 {
-        int missing;
-
-        missing = copy_from_user(dst, src, len);
-        if (missing) {
-                memset(dst + len - missing, 0, missing);
+        if (unlikely(copy_from_user(dst, src, len)))
                 *err_ptr = -EFAULT;
-        }
-                
         return csum_partial(dst, len, sum);
 }
 
diff --git a/arch/s390/include/asm/compat.h b/arch/s390/include/asm/compat.h
index 5d7e8cf83bd6..d350ed9d0fbb 100644
--- a/arch/s390/include/asm/compat.h
+++ b/arch/s390/include/asm/compat.h
@@ -8,7 +8,11 @@
 #include <linux/thread_info.h>
 
 #define __TYPE_IS_PTR(t) (!__builtin_types_compatible_p(typeof(0?(t)0:0ULL), u64))
-#define __SC_DELOUSE(t,v) (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v))
+
+#define __SC_DELOUSE(t,v) ({ \
+        BUILD_BUG_ON(sizeof(t) > 4 && !__TYPE_IS_PTR(t)); \
+        (t)(__TYPE_IS_PTR(t) ? ((v) & 0x7fffffff) : (v)); \
+})
 
 #define PSW32_MASK_PER          0x40000000UL
 #define PSW32_MASK_DAT          0x04000000UL
diff --git a/arch/s390/include/asm/futex.h b/arch/s390/include/asm/futex.h
index 51bcaa0fdeef..fda46bd38c99 100644
--- a/arch/s390/include/asm/futex.h
+++ b/arch/s390/include/asm/futex.h
@@ -5,7 +5,10 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
-static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newval);
+int __futex_atomic_op_inuser(int op, u32 __user *uaddr, int oparg, int *old);
+
+static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
         int op = (encoded_op >> 28) & 7;
         int cmp = (encoded_op >> 24) & 15;
@@ -17,7 +20,7 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
                 oparg = 1 << oparg;
 
         pagefault_disable();
-        ret = uaccess.futex_atomic_op(op, uaddr, oparg, &oldval);
+        ret = __futex_atomic_op_inuser(op, uaddr, oparg, &oldval);
         pagefault_enable();
 
         if (!ret) {
@@ -34,10 +37,4 @@ static inline int futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
         return ret;
 }
 
-static inline int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
-                                                u32 oldval, u32 newval)
-{
-        return uaccess.futex_atomic_cmpxchg(uval, uaddr, oldval, newval);
-}
-
 #endif /* _ASM_S390_FUTEX_H */
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index eef3dd3fd9a9..9bf95bb30f1a 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -106,7 +106,9 @@ struct kvm_s390_sie_block {
         __u64   gbea;                   /* 0x0180 */
         __u8    reserved188[24];        /* 0x0188 */
         __u32   fac;                    /* 0x01a0 */
-        __u8    reserved1a4[68];        /* 0x01a4 */
+        __u8    reserved1a4[20];        /* 0x01a4 */
+        __u64   cbrlo;                  /* 0x01b8 */
+        __u8    reserved1c0[40];        /* 0x01c0 */
         __u64   itdba;                  /* 0x01e8 */
         __u8    reserved1f0[16];        /* 0x01f0 */
 } __attribute__((packed));
@@ -155,6 +157,7 @@ struct kvm_vcpu_stat {
         u32 instruction_stsi;
         u32 instruction_stfl;
         u32 instruction_tprot;
+        u32 instruction_essa;
         u32 instruction_sigp_sense;
         u32 instruction_sigp_sense_running;
         u32 instruction_sigp_external_call;
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 5d1f950704dc..38149b63dc44 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -48,13 +48,42 @@ static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk)
 static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
                              struct task_struct *tsk)
 {
-        cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
-        update_mm(next, tsk);
+        int cpu = smp_processor_id();
+
+        if (prev == next)
+                return;
+        if (atomic_inc_return(&next->context.attach_count) >> 16) {
+                /* Delay update_mm until all TLB flushes are done. */
+                set_tsk_thread_flag(tsk, TIF_TLB_WAIT);
+        } else {
+                cpumask_set_cpu(cpu, mm_cpumask(next));
+                update_mm(next, tsk);
+                if (next->context.flush_mm)
+                        /* Flush pending TLBs */
+                        __tlb_flush_mm(next);
+        }
         atomic_dec(&prev->context.attach_count);
         WARN_ON(atomic_read(&prev->context.attach_count) < 0);
-        atomic_inc(&next->context.attach_count);
-        /* Check for TLBs not flushed yet */
-        __tlb_flush_mm_lazy(next);
+}
+
+#define finish_arch_post_lock_switch finish_arch_post_lock_switch
+static inline void finish_arch_post_lock_switch(void)
+{
+        struct task_struct *tsk = current;
+        struct mm_struct *mm = tsk->mm;
+
+        if (!test_tsk_thread_flag(tsk, TIF_TLB_WAIT))
+                return;
+        preempt_disable();
+        clear_tsk_thread_flag(tsk, TIF_TLB_WAIT);
+        while (atomic_read(&mm->context.attach_count) >> 16)
+                cpu_relax();
+
+        cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
+        update_mm(mm, tsk);
+        if (mm->context.flush_mm)
+                __tlb_flush_mm(mm);
+        preempt_enable();
 }
 
 #define enter_lazy_tlb(mm,tsk)  do { } while (0)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index e1408ddb94f8..884017cbfa9f 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -22,6 +22,7 @@ unsigned long *page_table_alloc(struct mm_struct *, unsigned long);
 void page_table_free(struct mm_struct *, unsigned long *);
 void page_table_free_rcu(struct mmu_gather *, unsigned long *);
 
+void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
                           unsigned long key, bool nq);
 
@@ -91,11 +92,22 @@ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long address)
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long vmaddr)
 {
         unsigned long *table = crst_table_alloc(mm);
-        if (table)
-                crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
+
+        if (!table)
+                return NULL;
+        crst_table_init(table, _SEGMENT_ENTRY_EMPTY);
+        if (!pgtable_pmd_page_ctor(virt_to_page(table))) {
+                crst_table_free(mm, table);
+                return NULL;
+        }
         return (pmd_t *) table;
 }
-#define pmd_free(mm, pmd) crst_table_free(mm, (unsigned long *) pmd)
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+        pgtable_pmd_page_dtor(virt_to_page(pmd));
+        crst_table_free(mm, (unsigned long *) pmd);
+}
 
 static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 2204400d0bd5..1ab75eaacbd4 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -229,6 +229,7 @@ extern unsigned long MODULES_END;
 #define _PAGE_READ      0x010           /* SW pte read bit */
 #define _PAGE_WRITE     0x020           /* SW pte write bit */
 #define _PAGE_SPECIAL   0x040           /* SW associated with special page */
+#define _PAGE_UNUSED    0x080           /* SW bit for pgste usage state */
 #define __HAVE_ARCH_PTE_SPECIAL
 
 /* Set of bits not changed in pte_modify */
@@ -394,6 +395,12 @@ extern unsigned long MODULES_END;
 
 #endif /* CONFIG_64BIT */
 
+/* Guest Page State used for virtualization */
+#define _PGSTE_GPS_ZERO         0x0000000080000000UL
+#define _PGSTE_GPS_USAGE_MASK   0x0000000003000000UL
+#define _PGSTE_GPS_USAGE_STABLE 0x0000000000000000UL
+#define _PGSTE_GPS_USAGE_UNUSED 0x0000000001000000UL
+
 /*
  * A user page table pointer has the space-switch-event bit, the
  * private-space-control bit and the storage-alteration-event-control
@@ -617,6 +624,14 @@ static inline int pte_none(pte_t pte)
         return pte_val(pte) == _PAGE_INVALID;
 }
 
+static inline int pte_swap(pte_t pte)
+{
+        /* Bit pattern: (pte & 0x603) == 0x402 */
+        return (pte_val(pte) & (_PAGE_INVALID | _PAGE_PROTECT |
+                                _PAGE_TYPE | _PAGE_PRESENT))
+                == (_PAGE_INVALID | _PAGE_TYPE);
+}
+
 static inline int pte_file(pte_t pte)
 {
         /* Bit pattern: (pte & 0x601) == 0x600 */
@@ -821,20 +836,20 @@ unsigned long gmap_translate(unsigned long address, struct gmap *);
 unsigned long __gmap_fault(unsigned long address, struct gmap *);
 unsigned long gmap_fault(unsigned long address, struct gmap *);
 void gmap_discard(unsigned long from, unsigned long to, struct gmap *);
+void __gmap_zap(unsigned long address, struct gmap *);
 
 void gmap_register_ipte_notifier(struct gmap_notifier *);
 void gmap_unregister_ipte_notifier(struct gmap_notifier *);
 int gmap_ipte_notify(struct gmap *, unsigned long start, unsigned long len);
-void gmap_do_ipte_notify(struct mm_struct *, unsigned long addr, pte_t *);
+void gmap_do_ipte_notify(struct mm_struct *, pte_t *);
 
 static inline pgste_t pgste_ipte_notify(struct mm_struct *mm,
-                                        unsigned long addr,
                                         pte_t *ptep, pgste_t pgste)
 {
 #ifdef CONFIG_PGSTE
         if (pgste_val(pgste) & PGSTE_IN_BIT) {
                 pgste_val(pgste) &= ~PGSTE_IN_BIT;
-                gmap_do_ipte_notify(mm, addr, ptep);
+                gmap_do_ipte_notify(mm, ptep);
         }
 #endif
         return pgste;
@@ -852,6 +867,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 
         if (mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
+                pgste_val(pgste) &= ~_PGSTE_GPS_ZERO;
                 pgste_set_key(ptep, pgste, entry);
                 pgste_set_pte(ptep, entry);
                 pgste_set_unlock(ptep, pgste);
@@ -881,6 +897,12 @@ static inline int pte_young(pte_t pte)
         return (pte_val(pte) & _PAGE_YOUNG) != 0;
 }
 
+#define __HAVE_ARCH_PTE_UNUSED
+static inline int pte_unused(pte_t pte)
+{
+        return pte_val(pte) & _PAGE_UNUSED;
+}
+
 /*
  * pgd/pmd/pte modification functions
  */
@@ -1034,30 +1056,41 @@ static inline int ptep_test_and_clear_user_young(struct mm_struct *mm,
 
 static inline void __ptep_ipte(unsigned long address, pte_t *ptep)
 {
-        if (!(pte_val(*ptep) & _PAGE_INVALID)) {
+        unsigned long pto = (unsigned long) ptep;
+
 #ifndef CONFIG_64BIT
-                /* pto must point to the start of the segment table */
-                pte_t *pto = (pte_t *) (((unsigned long) ptep) & 0x7ffffc00);
-#else
-                /* ipte in zarch mode can do the math */
-                pte_t *pto = ptep;
+        /* pto in ESA mode must point to the start of the segment table */
+        pto &= 0x7ffffc00;
 #endif
-                asm volatile(
-                        "       ipte    %2,%3"
-                        : "=m" (*ptep) : "m" (*ptep),
-                          "a" (pto), "a" (address));
-        }
+        /* Invalidation + global TLB flush for the pte */
+        asm volatile(
+                "       ipte    %2,%3"
+                : "=m" (*ptep) : "m" (*ptep), "a" (pto), "a" (address));
+}
+
+static inline void ptep_flush_direct(struct mm_struct *mm,
+                                     unsigned long address, pte_t *ptep)
+{
+        if (pte_val(*ptep) & _PAGE_INVALID)
+                return;
+        __ptep_ipte(address, ptep);
 }
 
 static inline void ptep_flush_lazy(struct mm_struct *mm,
                                    unsigned long address, pte_t *ptep)
 {
-        int active = (mm == current->active_mm) ? 1 : 0;
+        int active, count;
 
-        if (atomic_read(&mm->context.attach_count) > active)
-                __ptep_ipte(address, ptep);
-        else
+        if (pte_val(*ptep) & _PAGE_INVALID)
+                return;
+        active = (mm == current->active_mm) ? 1 : 0;
+        count = atomic_add_return(0x10000, &mm->context.attach_count);
+        if ((count & 0xffff) <= active) {
+                pte_val(*ptep) |= _PAGE_INVALID;
                 mm->context.flush_mm = 1;
+        } else
+                __ptep_ipte(address, ptep);
+        atomic_sub(0x10000, &mm->context.attach_count);
 }
 
 #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
@@ -1070,11 +1103,11 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma,
 
         if (mm_has_pgste(vma->vm_mm)) {
                 pgste = pgste_get_lock(ptep);
-                pgste = pgste_ipte_notify(vma->vm_mm, addr, ptep, pgste);
+                pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
         }
 
         pte = *ptep;
-        __ptep_ipte(addr, ptep);
+        ptep_flush_direct(vma->vm_mm, addr, ptep);
         young = pte_young(pte);
         pte = pte_mkold(pte);
 
@@ -1116,7 +1149,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
 
         if (mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
-                pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+                pgste = pgste_ipte_notify(mm, ptep, pgste);
         }
 
         pte = *ptep;
@@ -1140,12 +1173,11 @@ static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
 
         if (mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
-                pgste_ipte_notify(mm, address, ptep, pgste);
+                pgste_ipte_notify(mm, ptep, pgste);
         }
 
         pte = *ptep;
         ptep_flush_lazy(mm, address, ptep);
-        pte_val(*ptep) |= _PAGE_INVALID;
 
         if (mm_has_pgste(mm)) {
                 pgste = pgste_update_all(&pte, pgste);
@@ -1178,14 +1210,17 @@ static inline pte_t ptep_clear_flush(struct vm_area_struct *vma,
 
         if (mm_has_pgste(vma->vm_mm)) {
                 pgste = pgste_get_lock(ptep);
-                pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
+                pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
         }
 
         pte = *ptep;
-        __ptep_ipte(address, ptep);
+        ptep_flush_direct(vma->vm_mm, address, ptep);
         pte_val(*ptep) = _PAGE_INVALID;
 
         if (mm_has_pgste(vma->vm_mm)) {
+                if ((pgste_val(pgste) & _PGSTE_GPS_USAGE_MASK) ==
+                    _PGSTE_GPS_USAGE_UNUSED)
+                        pte_val(pte) |= _PAGE_UNUSED;
                 pgste = pgste_update_all(&pte, pgste);
                 pgste_set_unlock(ptep, pgste);
         }
@@ -1209,7 +1244,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 
         if (!full && mm_has_pgste(mm)) {
                 pgste = pgste_get_lock(ptep);
-                pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+                pgste = pgste_ipte_notify(mm, ptep, pgste);
         }
 
         pte = *ptep;
@@ -1234,7 +1269,7 @@ static inline pte_t ptep_set_wrprotect(struct mm_struct *mm,
         if (pte_write(pte)) {
                 if (mm_has_pgste(mm)) {
                         pgste = pgste_get_lock(ptep);
-                        pgste = pgste_ipte_notify(mm, address, ptep, pgste);
+                        pgste = pgste_ipte_notify(mm, ptep, pgste);
                 }
 
                 ptep_flush_lazy(mm, address, ptep);
@@ -1260,10 +1295,10 @@ static inline int ptep_set_access_flags(struct vm_area_struct *vma,
                 return 0;
         if (mm_has_pgste(vma->vm_mm)) {
                 pgste = pgste_get_lock(ptep);
-                pgste = pgste_ipte_notify(vma->vm_mm, address, ptep, pgste);
+                pgste = pgste_ipte_notify(vma->vm_mm, ptep, pgste);
         }
 
-        __ptep_ipte(address, ptep);
+        ptep_flush_direct(vma->vm_mm, address, ptep);
 
         if (mm_has_pgste(vma->vm_mm)) {
                 pgste_set_pte(ptep, entry);
@@ -1447,12 +1482,16 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 static inline void pmdp_flush_lazy(struct mm_struct *mm,
                                    unsigned long address, pmd_t *pmdp)
 {
-        int active = (mm == current->active_mm) ? 1 : 0;
+        int active, count;
 
-        if ((atomic_read(&mm->context.attach_count) & 0xffff) > active)
-                __pmd_idte(address, pmdp);
-        else
+        active = (mm == current->active_mm) ? 1 : 0;
+        count = atomic_add_return(0x10000, &mm->context.attach_count);
+        if ((count & 0xffff) <= active) {
+                pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
                 mm->context.flush_mm = 1;
+        } else
+                __pmd_idte(address, pmdp);
+        atomic_sub(0x10000, &mm->context.attach_count);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/s390/include/asm/ptrace.h b/arch/s390/include/asm/ptrace.h
index 9c82cebddabd..f4783c0b7b43 100644
--- a/arch/s390/include/asm/ptrace.h
+++ b/arch/s390/include/asm/ptrace.h
@@ -83,6 +83,7 @@ struct per_struct_kernel {
  * These are defined as per linux/ptrace.h, which see.
  */
 #define arch_has_single_step()  (1)
+#define arch_has_block_step()   (1)
 
 #define user_mode(regs) (((regs)->psw.mask & PSW_MASK_PSTATE) != 0)
 #define instruction_pointer(regs) ((regs)->psw.addr & PSW_ADDR_INSN)
diff --git a/arch/s390/include/asm/sclp.h b/arch/s390/include/asm/sclp.h
index abaca2275c7a..2f5e9932b4de 100644
--- a/arch/s390/include/asm/sclp.h
+++ b/arch/s390/include/asm/sclp.h
@@ -46,6 +46,7 @@ int sclp_cpu_configure(u8 cpu);
 int sclp_cpu_deconfigure(u8 cpu);
 unsigned long long sclp_get_rnmax(void);
 unsigned long long sclp_get_rzm(void);
+unsigned int sclp_get_max_cpu(void);
 int sclp_sdias_blk_count(void);
 int sclp_sdias_copy(void *dest, int blk_num, int nr_blks);
 int sclp_chp_configure(struct chp_id chpid);
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 94cfbe442f12..406f3a1e63ef 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -59,7 +59,6 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
 #define MACHINE_FLAG_DIAG44     (1UL << 4)
 #define MACHINE_FLAG_IDTE       (1UL << 5)
 #define MACHINE_FLAG_DIAG9C     (1UL << 6)
-#define MACHINE_FLAG_MVCOS      (1UL << 7)
 #define MACHINE_FLAG_KVM        (1UL << 8)
 #define MACHINE_FLAG_ESOP       (1UL << 9)
 #define MACHINE_FLAG_EDAT1      (1UL << 10)
@@ -85,7 +84,6 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
 #define MACHINE_HAS_IDTE        (0)
 #define MACHINE_HAS_DIAG44      (1)
 #define MACHINE_HAS_MVPG        (S390_lowcore.machine_flags & MACHINE_FLAG_MVPG)
-#define MACHINE_HAS_MVCOS       (0)
 #define MACHINE_HAS_EDAT1       (0)
 #define MACHINE_HAS_EDAT2       (0)
 #define MACHINE_HAS_LPP         (0)
@@ -98,7 +96,6 @@ void create_mem_hole(struct mem_chunk mem_chunk[], unsigned long addr,
 #define MACHINE_HAS_IDTE        (S390_lowcore.machine_flags & MACHINE_FLAG_IDTE)
 #define MACHINE_HAS_DIAG44      (S390_lowcore.machine_flags & MACHINE_FLAG_DIAG44)
 #define MACHINE_HAS_MVPG        (1)
-#define MACHINE_HAS_MVCOS       (S390_lowcore.machine_flags & MACHINE_FLAG_MVCOS)
 #define MACHINE_HAS_EDAT1       (S390_lowcore.machine_flags & MACHINE_FLAG_EDAT1)
 #define MACHINE_HAS_EDAT2       (S390_lowcore.machine_flags & MACHINE_FLAG_EDAT2)
 #define MACHINE_HAS_LPP         (S390_lowcore.machine_flags & MACHINE_FLAG_LPP)
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index 10e0fcd3633d..3ccd71b90345 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -81,6 +81,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NOTIFY_RESUME       1       /* callback before returning to user */
 #define TIF_SIGPENDING          2       /* signal pending */
 #define TIF_NEED_RESCHED        3       /* rescheduling necessary */
+#define TIF_TLB_WAIT            4       /* wait for TLB flush completion */
 #define TIF_PER_TRAP            6       /* deliver sigtrap on return to user */
 #define TIF_MCCK_PENDING        7       /* machine check handling is pending */
 #define TIF_SYSCALL_TRACE       8       /* syscall trace active */
@@ -91,11 +92,13 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE              18      /* is terminating due to OOM killer */
 #define TIF_RESTORE_SIGMASK     19      /* restore signal mask in do_signal() */
 #define TIF_SINGLE_STEP         20      /* This task is single stepped */
+#define TIF_BLOCK_STEP          21      /* This task is block stepped */
 
 #define _TIF_SYSCALL            (1<<TIF_SYSCALL)
 #define _TIF_NOTIFY_RESUME      (1<<TIF_NOTIFY_RESUME)
 #define _TIF_SIGPENDING         (1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED       (1<<TIF_NEED_RESCHED)
+#define _TIF_TLB_WAIT           (1<<TIF_TLB_WAIT)
 #define _TIF_PER_TRAP           (1<<TIF_PER_TRAP)
 #define _TIF_MCCK_PENDING       (1<<TIF_MCCK_PENDING)
 #define _TIF_SYSCALL_TRACE      (1<<TIF_SYSCALL_TRACE)
diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h
index 79330af9a5f8..4133b3f72fb0 100644
--- a/arch/s390/include/asm/uaccess.h
+++ b/arch/s390/include/asm/uaccess.h
@@ -92,33 +92,58 @@ static inline unsigned long extable_fixup(const struct exception_table_entry *x)
 #define ARCH_HAS_SORT_EXTABLE
 #define ARCH_HAS_SEARCH_EXTABLE
 
-struct uaccess_ops {
-        size_t (*copy_from_user)(size_t, const void __user *, void *);
-        size_t (*copy_to_user)(size_t, void __user *, const void *);
-        size_t (*copy_in_user)(size_t, void __user *, const void __user *);
-        size_t (*clear_user)(size_t, void __user *);
-        size_t (*strnlen_user)(size_t, const char __user *);
-        size_t (*strncpy_from_user)(size_t, const char __user *, char *);
-        int (*futex_atomic_op)(int op, u32 __user *, int oparg, int *old);
-        int (*futex_atomic_cmpxchg)(u32 *, u32 __user *, u32 old, u32 new);
-};
+int __handle_fault(unsigned long, unsigned long, int);
 
-extern struct uaccess_ops uaccess;
-extern struct uaccess_ops uaccess_mvcos;
-extern struct uaccess_ops uaccess_pt;
+/**
+ * __copy_from_user: - Copy a block of data from user space, with less checking.
+ * @to:   Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Copy data from user space to kernel space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ */
+unsigned long __must_check __copy_from_user(void *to, const void __user *from,
+                                            unsigned long n);
+
+/**
+ * __copy_to_user: - Copy a block of data into user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Copy data from kernel space to user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ */
+unsigned long __must_check __copy_to_user(void __user *to, const void *from,
+                                          unsigned long n);
 
-extern int __handle_fault(unsigned long, unsigned long, int);
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
 
-static inline int __put_user_fn(size_t size, void __user *ptr, void *x)
+static inline int __put_user_fn(void *x, void __user *ptr, unsigned long size)
 {
-        size = uaccess.copy_to_user(size, ptr, x);
-        return size ? -EFAULT : size;
+        size = __copy_to_user(ptr, x, size);
+        return size ? -EFAULT : 0;
 }
 
-static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
+static inline int __get_user_fn(void *x, const void __user *ptr, unsigned long size)
 {
-        size = uaccess.copy_from_user(size, ptr, x);
-        return size ? -EFAULT : size;
+        size = __copy_from_user(x, ptr, size);
+        return size ? -EFAULT : 0;
 }
 
 /*
@@ -135,8 +160,8 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
         case 2:                                                 \
         case 4:                                                 \
         case 8:                                                 \
-                __pu_err = __put_user_fn(sizeof (*(ptr)),       \
-                                         ptr, &__x);            \
+                __pu_err = __put_user_fn(&__x, ptr,             \
+                                         sizeof(*(ptr)));       \
                 break;                                          \
         default:                                                \
                 __put_user_bad();                               \
@@ -152,7 +177,7 @@ static inline int __get_user_fn(size_t size, const void __user *ptr, void *x)
 })
 
 
-extern int __put_user_bad(void) __attribute__((noreturn));
+int __put_user_bad(void) __attribute__((noreturn));
 
 #define __get_user(x, ptr)                                      \
 ({                                                              \
@@ -161,29 +186,29 @@ extern int __put_user_bad(void) __attribute__((noreturn));
         switch (sizeof(*(ptr))) {                               \
         case 1: {                                               \
                 unsigned char __x;                              \
-                __gu_err = __get_user_fn(sizeof (*(ptr)),       \
-                                         ptr, &__x);            \
+                __gu_err = __get_user_fn(&__x, ptr,             \
+                                         sizeof(*(ptr)));       \
                 (x) = *(__force __typeof__(*(ptr)) *) &__x;     \
                 break;                                          \
         };                                                      \
         case 2: {                                               \
                 unsigned short __x;                             \
-                __gu_err = __get_user_fn(sizeof (*(ptr)),       \
-                                         ptr, &__x);            \
+                __gu_err = __get_user_fn(&__x, ptr,             \
+                                         sizeof(*(ptr)));       \
                 (x) = *(__force __typeof__(*(ptr)) *) &__x;     \
                 break;                                          \
         };                                                      \
         case 4: {                                               \
                 unsigned int __x;                               \
-                __gu_err = __get_user_fn(sizeof (*(ptr)),       \
-                                         ptr, &__x);            \
+                __gu_err = __get_user_fn(&__x, ptr,             \
+                                         sizeof(*(ptr)));       \
                 (x) = *(__force __typeof__(*(ptr)) *) &__x;     \
                 break;                                          \
         };                                                      \
         case 8: {                                               \
                 unsigned long long __x;                         \
-                __gu_err = __get_user_fn(sizeof (*(ptr)),       \
-                                         ptr, &__x);            \
+                __gu_err = __get_user_fn(&__x, ptr,             \
+                                         sizeof(*(ptr)));       \
                 (x) = *(__force __typeof__(*(ptr)) *) &__x;     \
                 break;                                          \
         };                                                      \
@@ -200,35 +225,12 @@ extern int __put_user_bad(void) __attribute__((noreturn));
         __get_user(x, ptr);                                     \
 })
 
-extern int __get_user_bad(void) __attribute__((noreturn));
+int __get_user_bad(void) __attribute__((noreturn));
 
 #define __put_user_unaligned __put_user
 #define __get_user_unaligned __get_user
 
 /**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only.  This function may sleep.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-static inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-        return uaccess.copy_to_user(n, to, from);
-}
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-/**
  * copy_to_user: - Copy a block of data into user space.
  * @to:   Destination address, in user space.
  * @from: Source address, in kernel space.
@@ -248,30 +250,7 @@ copy_to_user(void __user *to, const void *from, unsigned long n)
         return __copy_to_user(to, from, n);
 }
 
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only.  This function may sleep.
- *
- * Copy data from user space to kernel space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- */
-static inline unsigned long __must_check
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-        return uaccess.copy_from_user(n, from, to);
-}
-
-extern void copy_from_user_overflow(void)
+void copy_from_user_overflow(void)
 #ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
 __compiletime_warning("copy_from_user() buffer size is not provably correct")
 #endif
@@ -306,11 +285,8 @@ copy_from_user(void *to, const void __user *from, unsigned long n)
         return __copy_from_user(to, from, n);
 }
 
-static inline unsigned long __must_check
-__copy_in_user(void __user *to, const void __user *from, unsigned long n)
-{
-        return uaccess.copy_in_user(n, to, from);
-}
+unsigned long __must_check
+__copy_in_user(void __user *to, const void __user *from, unsigned long n);
 
 static inline unsigned long __must_check
 copy_in_user(void __user *to, const void __user *from, unsigned long n)
@@ -322,18 +298,22 @@ copy_in_user(void __user *to, const void __user *from, unsigned long n)
 /*
  * Copy a null terminated string from userspace.
  */
+
+long __strncpy_from_user(char *dst, const char __user *src, long count);
+
 static inline long __must_check
 strncpy_from_user(char *dst, const char __user *src, long count)
 {
         might_fault();
-        return uaccess.strncpy_from_user(count, src, dst);
+        return __strncpy_from_user(dst, src, count);
 }
 
-static inline unsigned long
-strnlen_user(const char __user * src, unsigned long n)
+unsigned long __must_check __strnlen_user(const char __user *src, unsigned long count);
+
+static inline unsigned long strnlen_user(const char __user *src, unsigned long n)
 {
         might_fault();
-        return uaccess.strnlen_user(n, src);
+        return __strnlen_user(src, n);
 }
 
 /**
@@ -355,21 +335,14 @@ strnlen_user(const char __user * src, unsigned long n)
 /*
  * Zero Userspace
  */
+unsigned long __must_check __clear_user(void __user *to, unsigned long size);
 
-static inline unsigned long __must_check
-__clear_user(void __user *to, unsigned long n)
-{
-        return uaccess.clear_user(n, to);
-}
-
-static inline unsigned long __must_check
-clear_user(void __user *to, unsigned long n)
+static inline unsigned long __must_check clear_user(void __user *to, unsigned long n)
 {
         might_fault();
-        return uaccess.clear_user(n, to);
+        return __clear_user(to, n);
 }
 
-extern int copy_to_user_real(void __user *dest, void *src, size_t count);
-extern int copy_from_user_real(void *dest, void __user *src, size_t count);
+int copy_to_user_real(void __user *dest, void *src, unsigned long count);
 
 #endif /* __S390_UACCESS_H */
diff --git a/arch/s390/include/uapi/asm/ptrace.h b/arch/s390/include/uapi/asm/ptrace.h
index 7e0b498a2c2b..a150f4fabe43 100644
--- a/arch/s390/include/uapi/asm/ptrace.h
+++ b/arch/s390/include/uapi/asm/ptrace.h
@@ -403,6 +403,12 @@ typedef struct
 #define PTRACE_TE_ABORT_RAND          0x5011
 
 /*
+ * The numbers chosen here are somewhat arbitrary but absolutely MUST
+ * not overlap with any of the number assigned in <linux/ptrace.h>.
+ */
+#define PTRACE_SINGLEBLOCK      12      /* resume execution until next branch */
+
+/*
  * PT_PROT definition is loosely based on hppa bsd definition in
  * gdb/hppab-nat.c
  */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 1b3ac09c11b6..a95c4ca99617 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -47,9 +47,8 @@ obj-$(CONFIG_SCHED_BOOK)	+= topology.o
 obj-$(CONFIG_HIBERNATION)       += suspend.o swsusp_asm64.o
 obj-$(CONFIG_AUDIT)             += audit.o
 compat-obj-$(CONFIG_AUDIT)      += compat_audit.o
-obj-$(CONFIG_COMPAT)            += compat_linux.o compat_signal.o \
-                                        compat_wrapper.o compat_exec_domain.o \
-                                        $(compat-obj-y)
+obj-$(CONFIG_COMPAT)            += compat_linux.o compat_signal.o
+obj-$(CONFIG_COMPAT)            += compat_wrapper.o $(compat-obj-y)
 
 obj-$(CONFIG_STACKTRACE)        += stacktrace.o
 obj-$(CONFIG_KPROBES)           += kprobes.o
diff --git a/arch/s390/kernel/compat_exec_domain.c b/arch/s390/kernel/compat_exec_domain.c
deleted file mode 100644
index 765fabdada9f..000000000000
--- a/arch/s390/kernel/compat_exec_domain.c
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Support for 32-bit Linux for S390 personality.
- *
- * Copyright IBM Corp. 2000
- * Author(s): Gerhard Tonn (ton@de.ibm.com)
- *
- *
- */
-
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/personality.h>
-#include <linux/sched.h>
-
-static struct exec_domain s390_exec_domain;
-
-static int __init s390_init (void)
-{
-        s390_exec_domain.name = "Linux/s390";
-        s390_exec_domain.handler = NULL;
-        s390_exec_domain.pers_low = PER_LINUX32;
-        s390_exec_domain.pers_high = PER_LINUX32;
-        s390_exec_domain.signal_map = default_exec_domain.signal_map;
-        s390_exec_domain.signal_invmap = default_exec_domain.signal_invmap;
-        register_exec_domain(&s390_exec_domain);
-        return 0;
-}
-
-__initcall(s390_init);
diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c
index db02052bd137..ca38139423ae 100644
--- a/arch/s390/kernel/compat_linux.c
+++ b/arch/s390/kernel/compat_linux.c
@@ -86,48 +86,51 @@
 #define SET_STAT_UID(stat, uid)         (stat).st_uid = high2lowuid(uid)
 #define SET_STAT_GID(stat, gid)         (stat).st_gid = high2lowgid(gid)
 
-asmlinkage long sys32_chown16(const char __user * filename, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_chown16, const char __user *, filename,
+                       u16, user, u16, group)
 {
         return sys_chown(filename, low2highuid(user), low2highgid(group));
 }
 
-asmlinkage long sys32_lchown16(const char __user * filename, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_lchown16, const char __user *,
+                       filename, u16, user, u16, group)
 {
         return sys_lchown(filename, low2highuid(user), low2highgid(group));
 }
 
-asmlinkage long sys32_fchown16(unsigned int fd, u16 user, u16 group)
+COMPAT_SYSCALL_DEFINE3(s390_fchown16, unsigned int, fd, u16, user, u16, group)
 {
         return sys_fchown(fd, low2highuid(user), low2highgid(group));
 }
 
-asmlinkage long sys32_setregid16(u16 rgid, u16 egid)
+COMPAT_SYSCALL_DEFINE2(s390_setregid16, u16, rgid, u16, egid)
 {
         return sys_setregid(low2highgid(rgid), low2highgid(egid));
 }
 
-asmlinkage long sys32_setgid16(u16 gid)
+COMPAT_SYSCALL_DEFINE1(s390_setgid16, u16, gid)
 {
         return sys_setgid((gid_t)gid);
 }
 
-asmlinkage long sys32_setreuid16(u16 ruid, u16 euid)
+COMPAT_SYSCALL_DEFINE2(s390_setreuid16, u16, ruid, u16, euid)
 {
         return sys_setreuid(low2highuid(ruid), low2highuid(euid));
 }
 
-asmlinkage long sys32_setuid16(u16 uid)
+COMPAT_SYSCALL_DEFINE1(s390_setuid16, u16, uid)
 {
         return sys_setuid((uid_t)uid);
 }
 
-asmlinkage long sys32_setresuid16(u16 ruid, u16 euid, u16 suid)
+COMPAT_SYSCALL_DEFINE3(s390_setresuid16, u16, ruid, u16, euid, u16, suid)
 {
         return sys_setresuid(low2highuid(ruid), low2highuid(euid),
-                low2highuid(suid));
+                             low2highuid(suid));
 }
 
-asmlinkage long sys32_getresuid16(u16 __user *ruidp, u16 __user *euidp, u16 __user *suidp)
+COMPAT_SYSCALL_DEFINE3(s390_getresuid16, u16 __user *, ruidp,
+                       u16 __user *, euidp, u16 __user *, suidp)
 {
         const struct cred *cred = current_cred();
         int retval;
@@ -144,13 +147,14 @@ asmlinkage long sys32_getresuid16(u16 __user *ruidp, u16 __user *euidp, u16 __us
         return retval;
 }
 
-asmlinkage long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid)
+COMPAT_SYSCALL_DEFINE3(s390_setresgid16, u16, rgid, u16, egid, u16, sgid)
 {
         return sys_setresgid(low2highgid(rgid), low2highgid(egid),
-                low2highgid(sgid));
+                             low2highgid(sgid));
 }
 
-asmlinkage long sys32_getresgid16(u16 __user *rgidp, u16 __user *egidp, u16 __user *sgidp)
+COMPAT_SYSCALL_DEFINE3(s390_getresgid16, u16 __user *, rgidp,
+                       u16 __user *, egidp, u16 __user *, sgidp)
 {
         const struct cred *cred = current_cred();
         int retval;
@@ -167,12 +171,12 @@ asmlinkage long sys32_getresgid16(u16 __user *rgidp, u16 __user *egidp, u16 __us
         return retval;
 }
 
-asmlinkage long sys32_setfsuid16(u16 uid)
+COMPAT_SYSCALL_DEFINE1(s390_setfsuid16, u16, uid)
 {
         return sys_setfsuid((uid_t)uid);
 }
 
-asmlinkage long sys32_setfsgid16(u16 gid)
+COMPAT_SYSCALL_DEFINE1(s390_setfsgid16, u16, gid)
 {
         return sys_setfsgid((gid_t)gid);
 }
@@ -215,7 +219,7 @@ static int groups16_from_user(struct group_info *group_info, u16 __user *groupli
         return 0;
 }
 
-asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist)
+COMPAT_SYSCALL_DEFINE2(s390_getgroups16, int, gidsetsize, u16 __user *, grouplist)
 {
         const struct cred *cred = current_cred();
         int i;
@@ -240,7 +244,7 @@ out:
         return i;
 }
 
-asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
+COMPAT_SYSCALL_DEFINE2(s390_setgroups16, int, gidsetsize, u16 __user *, grouplist)
 {
         struct group_info *group_info;
         int retval;
@@ -265,22 +269,22 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist)
         return retval;
 }
 
-asmlinkage long sys32_getuid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getuid16)
 {
         return high2lowuid(from_kuid_munged(current_user_ns(), current_uid()));
 }
 
-asmlinkage long sys32_geteuid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_geteuid16)
 {
         return high2lowuid(from_kuid_munged(current_user_ns(), current_euid()));
 }
 
-asmlinkage long sys32_getgid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getgid16)
 {
         return high2lowgid(from_kgid_munged(current_user_ns(), current_gid()));
 }
 
-asmlinkage long sys32_getegid16(void)
+COMPAT_SYSCALL_DEFINE0(s390_getegid16)
 {
         return high2lowgid(from_kgid_munged(current_user_ns(), current_egid()));
 }
@@ -295,41 +299,35 @@ COMPAT_SYSCALL_DEFINE5(s390_ipc, uint, call, int, first, compat_ulong_t, second,
 }
 #endif
 
-asmlinkage long sys32_truncate64(const char __user * path, unsigned long high, unsigned long low)
+COMPAT_SYSCALL_DEFINE3(s390_truncate64, const char __user *, path, u32, high, u32, low)
 {
-        if ((int)high < 0)
-                return -EINVAL;
-        else
-                return sys_truncate(path, (high << 32) | low);
+        return sys_truncate(path, (unsigned long)high << 32 | low);
 }
 
-asmlinkage long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low)
+COMPAT_SYSCALL_DEFINE3(s390_ftruncate64, unsigned int, fd, u32, high, u32, low)
 {
-        if ((int)high < 0)
-                return -EINVAL;
-        else
-                return sys_ftruncate(fd, (high << 32) | low);
+        return sys_ftruncate(fd, (unsigned long)high << 32 | low);
 }
 
-asmlinkage long sys32_pread64(unsigned int fd, char __user *ubuf,
-                                size_t count, u32 poshi, u32 poslo)
+COMPAT_SYSCALL_DEFINE5(s390_pread64, unsigned int, fd, char __user *, ubuf,
+                       compat_size_t, count, u32, high, u32, low)
 {
         if ((compat_ssize_t) count < 0)
                 return -EINVAL;
-        return sys_pread64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo));
+        return sys_pread64(fd, ubuf, count, (unsigned long)high << 32 | low);
 }
 
-asmlinkage long sys32_pwrite64(unsigned int fd, const char __user *ubuf,
-                                size_t count, u32 poshi, u32 poslo)
+COMPAT_SYSCALL_DEFINE5(s390_pwrite64, unsigned int, fd, const char __user *, ubuf,
+                       compat_size_t, count, u32, high, u32, low)
 {
         if ((compat_ssize_t) count < 0)
                 return -EINVAL;
-        return sys_pwrite64(fd, ubuf, count, ((loff_t)AA(poshi) << 32) | AA(poslo));
+        return sys_pwrite64(fd, ubuf, count, (unsigned long)high << 32 | low);
 }
 
-asmlinkage compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count)
+COMPAT_SYSCALL_DEFINE4(s390_readahead, int, fd, u32, high, u32, low, s32, count)
 {
-        return sys_readahead(fd, ((loff_t)AA(offhi) << 32) | AA(offlo), count);
+        return sys_readahead(fd, (unsigned long)high << 32 | low, count);
 }
 
 struct stat64_emu31 {
@@ -381,7 +379,7 @@ static int cp_stat64(struct stat64_emu31 __user *ubuf, struct kstat *stat)
         return copy_to_user(ubuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; 
 }
 
-asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_stat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf)
 {
         struct kstat stat;
         int ret = vfs_stat(filename, &stat);
@@ -390,7 +388,7 @@ asmlinkage long sys32_stat64(const char __user * filename, struct stat64_emu31 _
         return ret;
 }
 
-asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_lstat64, const char __user *, filename, struct stat64_emu31 __user *, statbuf)
 {
         struct kstat stat;
         int ret = vfs_lstat(filename, &stat);
@@ -399,7 +397,7 @@ asmlinkage long sys32_lstat64(const char __user * filename, struct stat64_emu31
         return ret;
 }
 
-asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf)
+COMPAT_SYSCALL_DEFINE2(s390_fstat64, unsigned int, fd, struct stat64_emu31 __user *, statbuf)
 {
         struct kstat stat;
         int ret = vfs_fstat(fd, &stat);
@@ -408,8 +406,8 @@ asmlinkage long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * sta
         return ret;
 }
 
-asmlinkage long sys32_fstatat64(unsigned int dfd, const char __user *filename,
-                                struct stat64_emu31 __user* statbuf, int flag)
+COMPAT_SYSCALL_DEFINE4(s390_fstatat64, unsigned int, dfd, const char __user *, filename,
+                       struct stat64_emu31 __user *, statbuf, int, flag)
 {
         struct kstat stat;
         int error;
@@ -435,7 +433,7 @@ struct mmap_arg_struct_emu31 {
         compat_ulong_t offset;
 };
 
-asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg)
+COMPAT_SYSCALL_DEFINE1(s390_old_mmap, struct mmap_arg_struct_emu31 __user *, arg)
 {
         struct mmap_arg_struct_emu31 a;
 
@@ -447,7 +445,7 @@ asmlinkage unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg)
                               a.offset >> PAGE_SHIFT);
 }
 
-asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg)
+COMPAT_SYSCALL_DEFINE1(s390_mmap2, struct mmap_arg_struct_emu31 __user *, arg)
 {
         struct mmap_arg_struct_emu31 a;
 
@@ -456,7 +454,7 @@ asmlinkage long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg)
         return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd, a.offset);
 }
 
-asmlinkage long sys32_read(unsigned int fd, char __user * buf, size_t count)
+COMPAT_SYSCALL_DEFINE3(s390_read, unsigned int, fd, char __user *, buf, compat_size_t, count)
 {
         if ((compat_ssize_t) count < 0)
                 return -EINVAL; 
@@ -464,7 +462,7 @@ asmlinkage long sys32_read(unsigned int fd, char __user * buf, size_t count)
         return sys_read(fd, buf, count);
 }
 
-asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t count)
+COMPAT_SYSCALL_DEFINE3(s390_write, unsigned int, fd, const char __user *, buf, compat_size_t, count)
 {
         if ((compat_ssize_t) count < 0)
                 return -EINVAL; 
@@ -478,14 +476,13 @@ asmlinkage long sys32_write(unsigned int fd, const char __user * buf, size_t cou
  * because the 31 bit values differ from the 64 bit values.
  */
 
-asmlinkage long
-sys32_fadvise64(int fd, loff_t offset, size_t len, int advise)
+COMPAT_SYSCALL_DEFINE5(s390_fadvise64, int, fd, u32, high, u32, low, compat_size_t, len, int, advise)
 {
         if (advise == 4)
                 advise = POSIX_FADV_DONTNEED;
         else if (advise == 5)
                 advise = POSIX_FADV_NOREUSE;
-        return sys_fadvise64(fd, offset, len, advise);
+        return sys_fadvise64(fd, (unsigned long)high << 32 | low, len, advise);
 }
 
 struct fadvise64_64_args {
@@ -495,8 +492,7 @@ struct fadvise64_64_args {
         int advice;
 };
 
-asmlinkage long
-sys32_fadvise64_64(struct fadvise64_64_args __user *args)
+COMPAT_SYSCALL_DEFINE1(s390_fadvise64_64, struct fadvise64_64_args __user *, args)
 {
         struct fadvise64_64_args a;
 
@@ -508,3 +504,17 @@ sys32_fadvise64_64(struct fadvise64_64_args __user *args)
                 a.advice = POSIX_FADV_NOREUSE;
         return sys_fadvise64_64(a.fd, a.offset, a.len, a.advice);
 }
+
+COMPAT_SYSCALL_DEFINE6(s390_sync_file_range, int, fd, u32, offhigh, u32, offlow,
+                       u32, nhigh, u32, nlow, unsigned int, flags)
+{
+        return sys_sync_file_range(fd, ((loff_t)offhigh << 32) + offlow,
+                                   ((u64)nhigh << 32) + nlow, flags);
+}
+
+COMPAT_SYSCALL_DEFINE6(s390_fallocate, int, fd, int, mode, u32, offhigh, u32, offlow,
+                       u32, lenhigh, u32, lenlow)
+{
+        return sys_fallocate(fd, mode, ((loff_t)offhigh << 32) + offlow,
+                             ((u64)lenhigh << 32) + lenlow);
+}
diff --git a/arch/s390/kernel/compat_linux.h b/arch/s390/kernel/compat_linux.h
index 1bfda3eca379..39ddfdb40ae8 100644
--- a/arch/s390/kernel/compat_linux.h
+++ b/arch/s390/kernel/compat_linux.h
@@ -76,46 +76,43 @@ struct stat64_emu31;
 struct mmap_arg_struct_emu31;
 struct fadvise64_64_args;
 
-long sys32_chown16(const char __user * filename, u16 user, u16 group);
-long sys32_lchown16(const char __user * filename, u16 user, u16 group);
-long sys32_fchown16(unsigned int fd, u16 user, u16 group);
-long sys32_setregid16(u16 rgid, u16 egid);
-long sys32_setgid16(u16 gid);
-long sys32_setreuid16(u16 ruid, u16 euid);
-long sys32_setuid16(u16 uid);
-long sys32_setresuid16(u16 ruid, u16 euid, u16 suid);
-long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid);
-long sys32_setresgid16(u16 rgid, u16 egid, u16 sgid);
-long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid);
-long sys32_setfsuid16(u16 uid);
-long sys32_setfsgid16(u16 gid);
-long sys32_getgroups16(int gidsetsize, u16 __user *grouplist);
-long sys32_setgroups16(int gidsetsize, u16 __user *grouplist);
-long sys32_getuid16(void);
-long sys32_geteuid16(void);
-long sys32_getgid16(void);
-long sys32_getegid16(void);
-long sys32_truncate64(const char __user * path, unsigned long high,
-                      unsigned long low);
-long sys32_ftruncate64(unsigned int fd, unsigned long high, unsigned long low);
-long sys32_init_module(void __user *umod, unsigned long len,
-                       const char __user *uargs);
-long sys32_delete_module(const char __user *name_user, unsigned int flags);
-long sys32_pread64(unsigned int fd, char __user *ubuf, size_t count,
-                   u32 poshi, u32 poslo);
-long sys32_pwrite64(unsigned int fd, const char __user *ubuf,
-                    size_t count, u32 poshi, u32 poslo);
-compat_ssize_t sys32_readahead(int fd, u32 offhi, u32 offlo, s32 count);
-long sys32_stat64(const char __user * filename, struct stat64_emu31 __user * statbuf);
-long sys32_lstat64(const char __user * filename,
-                   struct stat64_emu31 __user * statbuf);
-long sys32_fstat64(unsigned long fd, struct stat64_emu31 __user * statbuf);
-long sys32_fstatat64(unsigned int dfd, const char __user *filename,
-                     struct stat64_emu31 __user* statbuf, int flag);
-unsigned long old32_mmap(struct mmap_arg_struct_emu31 __user *arg);
-long sys32_mmap2(struct mmap_arg_struct_emu31 __user *arg);
-long sys32_read(unsigned int fd, char __user * buf, size_t count);
-long sys32_write(unsigned int fd, const char __user * buf, size_t count);
-long sys32_fadvise64(int fd, loff_t offset, size_t len, int advise);
-long sys32_fadvise64_64(struct fadvise64_64_args __user *args);
+long compat_sys_s390_chown16(const char __user *filename, u16 user, u16 group);
+long compat_sys_s390_lchown16(const char __user *filename, u16 user, u16 group);
+long compat_sys_s390_fchown16(unsigned int fd, u16 user, u16 group);
+long compat_sys_s390_setregid16(u16 rgid, u16 egid);
+long compat_sys_s390_setgid16(u16 gid);
+long compat_sys_s390_setreuid16(u16 ruid, u16 euid);
+long compat_sys_s390_setuid16(u16 uid);
+long compat_sys_s390_setresuid16(u16 ruid, u16 euid, u16 suid);
+long compat_sys_s390_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user *suid);
+long compat_sys_s390_setresgid16(u16 rgid, u16 egid, u16 sgid);
+long compat_sys_s390_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user *sgid);
+long compat_sys_s390_setfsuid16(u16 uid);
+long compat_sys_s390_setfsgid16(u16 gid);
+long compat_sys_s390_getgroups16(int gidsetsize, u16 __user *grouplist);
+long compat_sys_s390_setgroups16(int gidsetsize, u16 __user *grouplist);
+long compat_sys_s390_getuid16(void);
+long compat_sys_s390_geteuid16(void);
+long compat_sys_s390_getgid16(void);
+long compat_sys_s390_getegid16(void);
+long compat_sys_s390_truncate64(const char __user *path, u32 high, u32 low);
+long compat_sys_s390_ftruncate64(unsigned int fd, u32 high, u32 low);
+long compat_sys_s390_pread64(unsigned int fd, char __user *ubuf, compat_size_t count, u32 high, u32 low);
+long compat_sys_s390_pwrite64(unsigned int fd, const char __user *ubuf, compat_size_t count, u32 high, u32 low);
+long compat_sys_s390_readahead(int fd, u32 high, u32 low, s32 count);
+long compat_sys_s390_stat64(const char __user *filename, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_lstat64(const char __user *filename, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_fstat64(unsigned int fd, struct stat64_emu31 __user *statbuf);
+long compat_sys_s390_fstatat64(unsigned int dfd, const char __user *filename, struct stat64_emu31 __user *statbuf, int flag);
+long compat_sys_s390_old_mmap(struct mmap_arg_struct_emu31 __user *arg);
+long compat_sys_s390_mmap2(struct mmap_arg_struct_emu31 __user *arg);
+long compat_sys_s390_read(unsigned int fd, char __user * buf, compat_size_t count);
+long compat_sys_s390_write(unsigned int fd, const char __user * buf, compat_size_t count);
+long compat_sys_s390_fadvise64(int fd, u32 high, u32 low, compat_size_t len, int advise);
+long compat_sys_s390_fadvise64_64(struct fadvise64_64_args __user *args);
+long compat_sys_s390_sync_file_range(int fd, u32 offhigh, u32 offlow, u32 nhigh, u32 nlow, unsigned int flags);
+long compat_sys_s390_fallocate(int fd, int mode, u32 offhigh, u32 offlow, u32 lenhigh, u32 lenlow);
+long compat_sys_sigreturn(void);
+long compat_sys_rt_sigreturn(void);
+
 #endif /* _ASM_S390X_S390_H */
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index 8b84bc373e94..7df5ed9f44d7 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -241,7 +241,7 @@ static int restore_sigregs_gprs_high(struct pt_regs *regs, __u32 __user *uregs)
         return 0;
 }
 
-asmlinkage long sys32_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(sigreturn)
 {
         struct pt_regs *regs = task_pt_regs(current);
         sigframe32 __user *frame = (sigframe32 __user *)regs->gprs[15];
@@ -260,7 +260,7 @@ badframe:
         return 0;
 }
 
-asmlinkage long sys32_rt_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 {
         struct pt_regs *regs = task_pt_regs(current);
         rt_sigframe32 __user *frame = (rt_sigframe32 __user *)regs->gprs[15];
diff --git a/arch/s390/kernel/compat_wrapper.S b/arch/s390/kernel/compat_wrapper.S
deleted file mode 100644
index 59c8efce1b99..000000000000
--- a/arch/s390/kernel/compat_wrapper.S
+++ /dev/null
@@ -1,1425 +0,0 @@
-/*
-*    wrapper for 31 bit compatible system calls.
-*
-*    Copyright IBM Corp. 2000, 2006
-*    Author(s): Gerhard Tonn (ton@de.ibm.com),
-*               Thomas Spatzier (tspat@de.ibm.com)
-*/
-
-#include <linux/linkage.h>
-
-ENTRY(sys32_exit_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_exit                # branch to sys_exit
-
-ENTRY(sys32_read_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # char *
-        llgfr   %r4,%r4                 # size_t
-        jg      sys32_read              # branch to sys_read
-
-ENTRY(sys32_write_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # const char *
-        llgfr   %r4,%r4                 # size_t
-        jg      sys32_write             # branch to system call
-
-ENTRY(sys32_close_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        jg      sys_close               # branch to system call
-
-ENTRY(sys32_creat_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        lgfr    %r3,%r3                 # int
-        jg      sys_creat               # branch to system call
-
-ENTRY(sys32_link_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgtr   %r3,%r3                 # const char *
-        jg      sys_link                # branch to system call
-
-ENTRY(sys32_unlink_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        jg      sys_unlink              # branch to system call
-
-ENTRY(sys32_chdir_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        jg      sys_chdir               # branch to system call
-
-ENTRY(sys32_time_wrapper)
-        llgtr   %r2,%r2                 # int *
-        jg      compat_sys_time         # branch to system call
-
-ENTRY(sys32_mknod_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        lgfr    %r3,%r3                 # int
-        llgfr   %r4,%r4                 # dev
-        jg      sys_mknod               # branch to system call
-
-ENTRY(sys32_chmod_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgfr   %r3,%r3                 # mode_t
-        jg      sys_chmod               # branch to system call
-
-ENTRY(sys32_lchown16_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgfr   %r3,%r3                 # __kernel_old_uid_emu31_t
-        llgfr   %r4,%r4                 # __kernel_old_uid_emu31_t
-        jg      sys32_lchown16          # branch to system call
-
-#sys32_getpid_wrapper                           # void
-
-ENTRY(sys32_mount_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # char *
-        llgfr   %r5,%r5                 # unsigned long
-        llgtr   %r6,%r6                 # void *
-        jg      compat_sys_mount        # branch to system call
-
-ENTRY(sys32_oldumount_wrapper)
-        llgtr   %r2,%r2                 # char *
-        jg      sys_oldumount           # branch to system call
-
-ENTRY(sys32_setuid16_wrapper)
-        llgfr   %r2,%r2                 # __kernel_old_uid_emu31_t
-        jg      sys32_setuid16          # branch to system call
-
-#sys32_getuid16_wrapper                 # void
-
-ENTRY(sys32_ptrace_wrapper)
-        lgfr    %r2,%r2                 # long
-        lgfr    %r3,%r3                 # long
-        llgtr   %r4,%r4                 # long
-        llgfr   %r5,%r5                 # long
-        jg      compat_sys_ptrace       # branch to system call
-
-ENTRY(sys32_alarm_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        jg      sys_alarm               # branch to system call
-
-ENTRY(compat_sys_utime_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # struct compat_utimbuf *
-        jg      compat_sys_utime        # branch to system call
-
-ENTRY(sys32_access_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        lgfr    %r3,%r3                 # int
-        jg      sys_access              # branch to system call
-
-ENTRY(sys32_nice_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_nice                # branch to system call
-
-#sys32_sync_wrapper                     # void
-
-ENTRY(sys32_kill_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        jg      sys_kill                # branch to system call
-
-ENTRY(sys32_rename_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgtr   %r3,%r3                 # const char *
-        jg      sys_rename              # branch to system call
-
-ENTRY(sys32_mkdir_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        lgfr    %r3,%r3                 # int
-        jg      sys_mkdir               # branch to system call
-
-ENTRY(sys32_rmdir_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        jg      sys_rmdir               # branch to system call
-
-ENTRY(sys32_dup_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        jg      sys_dup                 # branch to system call
-
-ENTRY(sys32_pipe_wrapper)
-        llgtr   %r2,%r2                 # u32 *
-        jg      sys_pipe                # branch to system call
-
-ENTRY(compat_sys_times_wrapper)
-        llgtr   %r2,%r2                 # struct compat_tms *
-        jg      compat_sys_times        # branch to system call
-
-ENTRY(sys32_brk_wrapper)
-        llgtr   %r2,%r2                 # unsigned long
-        jg      sys_brk                 # branch to system call
-
-ENTRY(sys32_setgid16_wrapper)
-        llgfr   %r2,%r2                 # __kernel_old_gid_emu31_t
-        jg      sys32_setgid16          # branch to system call
-
-#sys32_getgid16_wrapper                 # void
-
-ENTRY(sys32_signal_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # __sighandler_t
-        jg      sys_signal
-
-#sys32_geteuid16_wrapper                # void
-
-#sys32_getegid16_wrapper                # void
-
-ENTRY(sys32_acct_wrapper)
-        llgtr   %r2,%r2                 # char *
-        jg      sys_acct                # branch to system call
-
-ENTRY(sys32_umount_wrapper)
-        llgtr   %r2,%r2                 # char *
-        lgfr    %r3,%r3                 # int
-        jg      sys_umount              # branch to system call
-
-ENTRY(compat_sys_ioctl_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned int
-        llgfr   %r4,%r4                 # unsigned int
-        jg      compat_sys_ioctl        # branch to system call
-
-ENTRY(compat_sys_fcntl_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned int
-        llgfr   %r4,%r4                 # unsigned long
-        jg      compat_sys_fcntl        # branch to system call
-
-ENTRY(sys32_setpgid_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        lgfr    %r3,%r3                 # pid_t
-        jg      sys_setpgid             # branch to system call
-
-ENTRY(sys32_umask_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_umask               # branch to system call
-
-ENTRY(sys32_chroot_wrapper)
-        llgtr   %r2,%r2                 # char *
-        jg      sys_chroot              # branch to system call
-
-ENTRY(sys32_ustat_wrapper)
-        llgfr   %r2,%r2                 # dev_t
-        llgtr   %r3,%r3                 # struct ustat *
-        jg      compat_sys_ustat
-
-ENTRY(sys32_dup2_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned int
-        jg      sys_dup2                # branch to system call
-
-#sys32_getppid_wrapper                  # void
-
-#sys32_getpgrp_wrapper                  # void
-
-#sys32_setsid_wrapper                   # void
-
-ENTRY(sys32_setreuid16_wrapper)
-        llgfr   %r2,%r2                 # __kernel_old_uid_emu31_t
-        llgfr   %r3,%r3                 # __kernel_old_uid_emu31_t
-        jg      sys32_setreuid16        # branch to system call
-
-ENTRY(sys32_setregid16_wrapper)
-        llgfr   %r2,%r2                 # __kernel_old_gid_emu31_t
-        llgfr   %r3,%r3                 # __kernel_old_gid_emu31_t
-        jg      sys32_setregid16        # branch to system call
-
-ENTRY(sys_sigsuspend_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        llgfr   %r4,%r4                 # old_sigset_t
-        jg      sys_sigsuspend
-
-ENTRY(compat_sys_sigpending_wrapper)
-        llgtr   %r2,%r2                 # compat_old_sigset_t *
-        jg      compat_sys_sigpending   # branch to system call
-
-ENTRY(sys32_sethostname_wrapper)
-        llgtr   %r2,%r2                 # char *
-        lgfr    %r3,%r3                 # int
-        jg      sys_sethostname         # branch to system call
-
-ENTRY(compat_sys_setrlimit_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # struct rlimit_emu31 *
-        jg      compat_sys_setrlimit    # branch to system call
-
-ENTRY(compat_sys_old_getrlimit_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # struct rlimit_emu31 *
-        jg      compat_sys_old_getrlimit # branch to system call
-
-ENTRY(compat_sys_getrlimit_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # struct rlimit_emu31 *
-        jg      compat_sys_getrlimit    # branch to system call
-
-ENTRY(sys32_mmap2_wrapper)
-        llgtr   %r2,%r2                 # struct mmap_arg_struct_emu31 *
-        jg      sys32_mmap2                     # branch to system call
-
-ENTRY(compat_sys_gettimeofday_wrapper)
-        llgtr   %r2,%r2                 # struct timeval_emu31 *
-        llgtr   %r3,%r3                 # struct timezone *
-        jg      compat_sys_gettimeofday # branch to system call
-
-ENTRY(compat_sys_settimeofday_wrapper)
-        llgtr   %r2,%r2                 # struct timeval_emu31 *
-        llgtr   %r3,%r3                 # struct timezone *
-        jg      compat_sys_settimeofday # branch to system call
-
-ENTRY(sys32_getgroups16_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # __kernel_old_gid_emu31_t *
-        jg      sys32_getgroups16       # branch to system call
-
-ENTRY(sys32_setgroups16_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # __kernel_old_gid_emu31_t *
-        jg      sys32_setgroups16       # branch to system call
-
-ENTRY(sys32_symlink_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgtr   %r3,%r3                 # const char *
-        jg      sys_symlink             # branch to system call
-
-ENTRY(sys32_readlink_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgtr   %r3,%r3                 # char *
-        lgfr    %r4,%r4                 # int
-        jg      sys_readlink            # branch to system call
-
-ENTRY(sys32_uselib_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        jg      sys_uselib              # branch to system call
-
-ENTRY(sys32_swapon_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        lgfr    %r3,%r3                 # int
-        jg      sys_swapon              # branch to system call
-
-ENTRY(sys32_reboot_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        llgfr   %r4,%r4                 # unsigned int
-        llgtr   %r5,%r5                 # void *
-        jg      sys_reboot              # branch to system call
-
-ENTRY(old32_readdir_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # void *
-        llgfr   %r4,%r4                 # unsigned int
-        jg      compat_sys_old_readdir  # branch to system call
-
-ENTRY(old32_mmap_wrapper)
-        llgtr   %r2,%r2                 # struct mmap_arg_struct_emu31 *
-        jg      old32_mmap              # branch to system call
-
-ENTRY(sys32_munmap_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # size_t
-        jg      sys_munmap              # branch to system call
-
-ENTRY(sys32_fchmod_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # mode_t
-        jg      sys_fchmod              # branch to system call
-
-ENTRY(sys32_fchown16_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # compat_uid_t
-        llgfr   %r4,%r4                 # compat_uid_t
-        jg      sys32_fchown16          # branch to system call
-
-ENTRY(sys32_getpriority_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        jg      sys_getpriority         # branch to system call
-
-ENTRY(sys32_setpriority_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        lgfr    %r4,%r4                 # int
-        jg      sys_setpriority         # branch to system call
-
-ENTRY(compat_sys_statfs_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # struct compat_statfs *
-        jg      compat_sys_statfs       # branch to system call
-
-ENTRY(compat_sys_fstatfs_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # struct compat_statfs *
-        jg      compat_sys_fstatfs      # branch to system call
-
-ENTRY(compat_sys_socketcall_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # u32 *
-        jg      compat_sys_socketcall   # branch to system call
-
-ENTRY(sys32_syslog_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # char *
-        lgfr    %r4,%r4                 # int
-        jg      sys_syslog              # branch to system call
-
-ENTRY(compat_sys_newstat_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # struct stat_emu31 *
-        jg      compat_sys_newstat      # branch to system call
-
-ENTRY(compat_sys_newlstat_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # struct stat_emu31 *
-        jg      compat_sys_newlstat     # branch to system call
-
-ENTRY(compat_sys_newfstat_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # struct stat_emu31 *
-        jg      compat_sys_newfstat     # branch to system call
-
-#sys32_vhangup_wrapper                  # void
-
-ENTRY(sys32_swapoff_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        jg      sys_swapoff             # branch to system call
-
-ENTRY(compat_sys_sysinfo_wrapper)
-        llgtr   %r2,%r2                 # struct sysinfo_emu31 *
-        jg      compat_sys_sysinfo      # branch to system call
-
-ENTRY(sys32_fsync_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        jg      sys_fsync               # branch to system call
-
-#sys32_sigreturn_wrapper                # done in sigreturn_glue
-
-#sys32_clone_wrapper                    # done in clone_glue
-
-ENTRY(sys32_setdomainname_wrapper)
-        llgtr   %r2,%r2                 # char *
-        lgfr    %r3,%r3                 # int
-        jg      sys_setdomainname       # branch to system call
-
-ENTRY(sys32_newuname_wrapper)
-        llgtr   %r2,%r2                 # struct new_utsname *
-        jg      sys_newuname            # branch to system call
-
-ENTRY(compat_sys_adjtimex_wrapper)
-        llgtr   %r2,%r2                 # struct compat_timex *
-        jg      compat_sys_adjtimex     # branch to system call
-
-ENTRY(sys32_mprotect_wrapper)
-        llgtr   %r2,%r2                 # unsigned long (actually pointer
-        llgfr   %r3,%r3                 # size_t
-        llgfr   %r4,%r4                 # unsigned long
-        jg      sys_mprotect            # branch to system call
-
-ENTRY(sys_init_module_wrapper)
-        llgtr   %r2,%r2                 # void *
-        llgfr   %r3,%r3                 # unsigned long
-        llgtr   %r4,%r4                 # char *
-        jg      sys_init_module         # branch to system call
-
-ENTRY(sys_delete_module_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgfr   %r3,%r3                 # unsigned int
-        jg      sys_delete_module       # branch to system call
-
-ENTRY(sys32_quotactl_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # const char *
-        llgfr   %r4,%r4                 # qid_t
-        llgtr   %r5,%r5                 # caddr_t
-        jg      sys_quotactl            # branch to system call
-
-ENTRY(sys32_getpgid_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        jg      sys_getpgid             # branch to system call
-
-ENTRY(sys32_fchdir_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        jg      sys_fchdir              # branch to system call
-
-ENTRY(sys32_bdflush_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # long
-        jg      sys_bdflush             # branch to system call
-
-ENTRY(sys32_sysfs_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgfr   %r3,%r3                 # unsigned long
-        llgfr   %r4,%r4                 # unsigned long
-        jg      sys_sysfs               # branch to system call
-
-ENTRY(sys32_personality_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        jg      sys_s390_personality    # branch to system call
-
-ENTRY(sys32_setfsuid16_wrapper)
-        llgfr   %r2,%r2                 # __kernel_old_uid_emu31_t
-        jg      sys32_setfsuid16        # branch to system call
-
-ENTRY(sys32_setfsgid16_wrapper)
-        llgfr   %r2,%r2                 # __kernel_old_gid_emu31_t
-        jg      sys32_setfsgid16        # branch to system call
-
-ENTRY(sys32_llseek_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned long
-        llgfr   %r4,%r4                 # unsigned long
-        llgtr   %r5,%r5                 # loff_t *
-        llgfr   %r6,%r6                 # unsigned int
-        jg      sys_llseek              # branch to system call
-
-ENTRY(sys32_getdents_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # void *
-        llgfr   %r4,%r4                 # unsigned int
-        jg      compat_sys_getdents     # branch to system call
-
-ENTRY(compat_sys_select_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # compat_fd_set *
-        llgtr   %r4,%r4                 # compat_fd_set *
-        llgtr   %r5,%r5                 # compat_fd_set *
-        llgtr   %r6,%r6                 # struct compat_timeval *
-        jg      compat_sys_select       # branch to system call
-
-ENTRY(sys32_flock_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned int
-        jg      sys_flock               # branch to system call
-
-ENTRY(sys32_msync_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # size_t
-        lgfr    %r4,%r4                 # int
-        jg      sys_msync               # branch to system call
-
-ENTRY(compat_sys_readv_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const struct compat_iovec *
-        llgfr   %r4,%r4                 # unsigned long
-        jg      compat_sys_readv        # branch to system call
-
-ENTRY(compat_sys_writev_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const struct compat_iovec *
-        llgfr   %r4,%r4                 # unsigned long
-        jg      compat_sys_writev       # branch to system call
-
-ENTRY(sys32_getsid_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        jg      sys_getsid              # branch to system call
-
-ENTRY(sys32_fdatasync_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        jg      sys_fdatasync           # branch to system call
-
-ENTRY(sys32_mlock_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # size_t
-        jg      sys_mlock               # branch to system call
-
-ENTRY(sys32_munlock_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # size_t
-        jg      sys_munlock             # branch to system call
-
-ENTRY(sys32_mlockall_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_mlockall            # branch to system call
-
-#sys32_munlockall_wrapper               # void
-
-ENTRY(sys32_sched_setparam_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        llgtr   %r3,%r3                 # struct sched_param *
-        jg      sys_sched_setparam      # branch to system call
-
-ENTRY(sys32_sched_getparam_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        llgtr   %r3,%r3                 # struct sched_param *
-        jg      sys_sched_getparam      # branch to system call
-
-ENTRY(sys32_sched_setscheduler_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        lgfr    %r3,%r3                 # int
-        llgtr   %r4,%r4                 # struct sched_param *
-        jg      sys_sched_setscheduler  # branch to system call
-
-ENTRY(sys32_sched_getscheduler_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        jg      sys_sched_getscheduler  # branch to system call
-
-#sys32_sched_yield_wrapper              # void
-
-ENTRY(sys32_sched_get_priority_max_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_sched_get_priority_max      # branch to system call
-
-ENTRY(sys32_sched_get_priority_min_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_sched_get_priority_min      # branch to system call
-
-ENTRY(compat_sys_nanosleep_wrapper)
-        llgtr   %r2,%r2                 # struct compat_timespec *
-        llgtr   %r3,%r3                 # struct compat_timespec *
-        jg      compat_sys_nanosleep            # branch to system call
-
-ENTRY(sys32_mremap_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # unsigned long
-        llgfr   %r4,%r4                 # unsigned long
-        llgfr   %r5,%r5                 # unsigned long
-        llgfr   %r6,%r6                 # unsigned long
-        jg      sys_mremap              # branch to system call
-
-ENTRY(sys32_setresuid16_wrapper)
-        llgfr   %r2,%r2                 # __kernel_old_uid_emu31_t
-        llgfr   %r3,%r3                 # __kernel_old_uid_emu31_t
-        llgfr   %r4,%r4                 # __kernel_old_uid_emu31_t
-        jg      sys32_setresuid16       # branch to system call
-
-ENTRY(sys32_getresuid16_wrapper)
-        llgtr   %r2,%r2                 # __kernel_old_uid_emu31_t *
-        llgtr   %r3,%r3                 # __kernel_old_uid_emu31_t *
-        llgtr   %r4,%r4                 # __kernel_old_uid_emu31_t *
-        jg      sys32_getresuid16       # branch to system call
-
-ENTRY(sys32_poll_wrapper)
-        llgtr   %r2,%r2                 # struct pollfd *
-        llgfr   %r3,%r3                 # unsigned int
-        lgfr    %r4,%r4                 # int
-        jg      sys_poll                # branch to system call
-
-ENTRY(sys32_setresgid16_wrapper)
-        llgfr   %r2,%r2                 # __kernel_old_gid_emu31_t
-        llgfr   %r3,%r3                 # __kernel_old_gid_emu31_t
-        llgfr   %r4,%r4                 # __kernel_old_gid_emu31_t
-        jg      sys32_setresgid16       # branch to system call
-
-ENTRY(sys32_getresgid16_wrapper)
-        llgtr   %r2,%r2                 # __kernel_old_gid_emu31_t *
-        llgtr   %r3,%r3                 # __kernel_old_gid_emu31_t *
-        llgtr   %r4,%r4                 # __kernel_old_gid_emu31_t *
-        jg      sys32_getresgid16       # branch to system call
-
-ENTRY(sys32_prctl_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgfr   %r3,%r3                 # unsigned long
-        llgfr   %r4,%r4                 # unsigned long
-        llgfr   %r5,%r5                 # unsigned long
-        llgfr   %r6,%r6                 # unsigned long
-        jg      sys_prctl               # branch to system call
-
-#sys32_rt_sigreturn_wrapper             # done in rt_sigreturn_glue
-
-ENTRY(sys32_pread64_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # char *
-        llgfr   %r4,%r4                 # size_t
-        llgfr   %r5,%r5                 # u32
-        llgfr   %r6,%r6                 # u32
-        jg      sys32_pread64           # branch to system call
-
-ENTRY(sys32_pwrite64_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # const char *
-        llgfr   %r4,%r4                 # size_t
-        llgfr   %r5,%r5                 # u32
-        llgfr   %r6,%r6                 # u32
-        jg      sys32_pwrite64          # branch to system call
-
-ENTRY(sys32_chown16_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgfr   %r3,%r3                 # __kernel_old_uid_emu31_t
-        llgfr   %r4,%r4                 # __kernel_old_gid_emu31_t
-        jg      sys32_chown16           # branch to system call
-
-ENTRY(sys32_getcwd_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgfr   %r3,%r3                 # unsigned long
-        jg      sys_getcwd              # branch to system call
-
-ENTRY(sys32_capget_wrapper)
-        llgtr   %r2,%r2                 # cap_user_header_t
-        llgtr   %r3,%r3                 # cap_user_data_t
-        jg      sys_capget              # branch to system call
-
-ENTRY(sys32_capset_wrapper)
-        llgtr   %r2,%r2                 # cap_user_header_t
-        llgtr   %r3,%r3                 # const cap_user_data_t
-        jg      sys_capset              # branch to system call
-
-#sys32_vfork_wrapper                    # done in vfork_glue
-
-ENTRY(sys32_truncate64_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgfr   %r3,%r3                 # unsigned long
-        llgfr   %r4,%r4                 # unsigned long
-        jg      sys32_truncate64        # branch to system call
-
-ENTRY(sys32_ftruncate64_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned long
-        llgfr   %r4,%r4                 # unsigned long
-        jg      sys32_ftruncate64       # branch to system call
-
-ENTRY(sys32_lchown_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgfr   %r3,%r3                 # uid_t
-        llgfr   %r4,%r4                 # gid_t
-        jg      sys_lchown              # branch to system call
-
-#sys32_getuid_wrapper                   # void
-#sys32_getgid_wrapper                   # void
-#sys32_geteuid_wrapper                  # void
-#sys32_getegid_wrapper                  # void
-
-ENTRY(sys32_setreuid_wrapper)
-        llgfr   %r2,%r2                 # uid_t
-        llgfr   %r3,%r3                 # uid_t
-        jg      sys_setreuid            # branch to system call
-
-ENTRY(sys32_setregid_wrapper)
-        llgfr   %r2,%r2                 # gid_t
-        llgfr   %r3,%r3                 # gid_t
-        jg      sys_setregid            # branch to system call
-
-ENTRY(sys32_getgroups_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # gid_t *
-        jg      sys_getgroups           # branch to system call
-
-ENTRY(sys32_setgroups_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # gid_t *
-        jg      sys_setgroups           # branch to system call
-
-ENTRY(sys32_fchown_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # uid_t
-        llgfr   %r4,%r4                 # gid_t
-        jg      sys_fchown              # branch to system call
-
-ENTRY(sys32_setresuid_wrapper)
-        llgfr   %r2,%r2                 # uid_t
-        llgfr   %r3,%r3                 # uid_t
-        llgfr   %r4,%r4                 # uid_t
-        jg      sys_setresuid           # branch to system call
-
-ENTRY(sys32_getresuid_wrapper)
-        llgtr   %r2,%r2                 # uid_t *
-        llgtr   %r3,%r3                 # uid_t *
-        llgtr   %r4,%r4                 # uid_t *
-        jg      sys_getresuid           # branch to system call
-
-ENTRY(sys32_setresgid_wrapper)
-        llgfr   %r2,%r2                 # gid_t
-        llgfr   %r3,%r3                 # gid_t
-        llgfr   %r4,%r4                 # gid_t
-        jg      sys_setresgid           # branch to system call
-
-ENTRY(sys32_getresgid_wrapper)
-        llgtr   %r2,%r2                 # gid_t *
-        llgtr   %r3,%r3                 # gid_t *
-        llgtr   %r4,%r4                 # gid_t *
-        jg      sys_getresgid           # branch to system call
-
-ENTRY(sys32_chown_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgfr   %r3,%r3                 # uid_t
-        llgfr   %r4,%r4                 # gid_t
-        jg      sys_chown               # branch to system call
-
-ENTRY(sys32_setuid_wrapper)
-        llgfr   %r2,%r2                 # uid_t
-        jg      sys_setuid              # branch to system call
-
-ENTRY(sys32_setgid_wrapper)
-        llgfr   %r2,%r2                 # gid_t
-        jg      sys_setgid              # branch to system call
-
-ENTRY(sys32_setfsuid_wrapper)
-        llgfr   %r2,%r2                 # uid_t
-        jg      sys_setfsuid            # branch to system call
-
-ENTRY(sys32_setfsgid_wrapper)
-        llgfr   %r2,%r2                 # gid_t
-        jg      sys_setfsgid            # branch to system call
-
-ENTRY(sys32_pivot_root_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgtr   %r3,%r3                 # const char *
-        jg      sys_pivot_root          # branch to system call
-
-ENTRY(sys32_mincore_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # size_t
-        llgtr   %r4,%r4                 # unsigned char *
-        jg      sys_mincore             # branch to system call
-
-ENTRY(sys32_madvise_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # size_t
-        lgfr    %r4,%r4                 # int
-        jg      sys_madvise             # branch to system call
-
-ENTRY(sys32_getdents64_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # void *
-        llgfr   %r4,%r4                 # unsigned int
-        jg      sys_getdents64          # branch to system call
-
-ENTRY(compat_sys_fcntl64_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned int
-        llgfr   %r4,%r4                 # unsigned long
-        jg      compat_sys_fcntl64      # branch to system call
-
-ENTRY(sys32_stat64_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # struct stat64 *
-        jg      sys32_stat64            # branch to system call
-
-ENTRY(sys32_lstat64_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # struct stat64 *
-        jg      sys32_lstat64           # branch to system call
-
-ENTRY(sys32_stime_wrapper)
-        llgtr   %r2,%r2                 # long *
-        jg      compat_sys_stime        # branch to system call
-
-ENTRY(sys32_fstat64_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgtr   %r3,%r3                 # struct stat64 *
-        jg      sys32_fstat64           # branch to system call
-
-ENTRY(sys32_setxattr_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # void *
-        llgfr   %r5,%r5                 # size_t
-        lgfr    %r6,%r6                 # int
-        jg      sys_setxattr
-
-ENTRY(sys32_lsetxattr_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # void *
-        llgfr   %r5,%r5                 # size_t
-        lgfr    %r6,%r6                 # int
-        jg      sys_lsetxattr
-
-ENTRY(sys32_fsetxattr_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # void *
-        llgfr   %r5,%r5                 # size_t
-        lgfr    %r6,%r6                 # int
-        jg      sys_fsetxattr
-
-ENTRY(sys32_getxattr_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # void *
-        llgfr   %r5,%r5                 # size_t
-        jg      sys_getxattr
-
-ENTRY(sys32_lgetxattr_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # void *
-        llgfr   %r5,%r5                 # size_t
-        jg      sys_lgetxattr
-
-ENTRY(sys32_fgetxattr_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # void *
-        llgfr   %r5,%r5                 # size_t
-        jg      sys_fgetxattr
-
-ENTRY(sys32_listxattr_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        llgfr   %r4,%r4                 # size_t
-        jg      sys_listxattr
-
-ENTRY(sys32_llistxattr_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        llgfr   %r4,%r4                 # size_t
-        jg      sys_llistxattr
-
-ENTRY(sys32_flistxattr_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # char *
-        llgfr   %r4,%r4                 # size_t
-        jg      sys_flistxattr
-
-ENTRY(sys32_removexattr_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        jg      sys_removexattr
-
-ENTRY(sys32_lremovexattr_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # char *
-        jg      sys_lremovexattr
-
-ENTRY(sys32_fremovexattr_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # char *
-        jg      sys_fremovexattr
-
-ENTRY(sys32_sched_setaffinity_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgfr   %r3,%r3                 # unsigned int
-        llgtr   %r4,%r4                 # unsigned long *
-        jg      compat_sys_sched_setaffinity
-
-ENTRY(sys32_sched_getaffinity_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgfr   %r3,%r3                 # unsigned int
-        llgtr   %r4,%r4                 # unsigned long *
-        jg      compat_sys_sched_getaffinity
-
-ENTRY(sys32_exit_group_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_exit_group          # branch to system call
-
-ENTRY(sys32_set_tid_address_wrapper)
-        llgtr   %r2,%r2                 # int *
-        jg      sys_set_tid_address     # branch to system call
-
-ENTRY(sys_epoll_create_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_epoll_create        # branch to system call
-
-ENTRY(sys_epoll_ctl_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        lgfr    %r4,%r4                 # int
-        llgtr   %r5,%r5                 # struct epoll_event *
-        jg      sys_epoll_ctl           # branch to system call
-
-ENTRY(sys_epoll_wait_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # struct epoll_event *
-        lgfr    %r4,%r4                 # int
-        lgfr    %r5,%r5                 # int
-        jg      sys_epoll_wait          # branch to system call
-
-ENTRY(sys32_fadvise64_wrapper)
-        lgfr    %r2,%r2                 # int
-        sllg    %r3,%r3,32              # get high word of 64bit loff_t
-        or      %r3,%r4                 # get low word of 64bit loff_t
-        llgfr   %r4,%r5                 # size_t (unsigned long)
-        lgfr    %r5,%r6                 # int
-        jg      sys32_fadvise64
-
-ENTRY(sys32_fadvise64_64_wrapper)
-        llgtr   %r2,%r2                 # struct fadvise64_64_args *
-        jg      sys32_fadvise64_64
-
-ENTRY(sys32_clock_settime_wrapper)
-        lgfr    %r2,%r2                 # clockid_t (int)
-        llgtr   %r3,%r3                 # struct compat_timespec *
-        jg      compat_sys_clock_settime
-
-ENTRY(sys32_clock_gettime_wrapper)
-        lgfr    %r2,%r2                 # clockid_t (int)
-        llgtr   %r3,%r3                 # struct compat_timespec *
-        jg      compat_sys_clock_gettime
-
-ENTRY(sys32_clock_getres_wrapper)
-        lgfr    %r2,%r2                 # clockid_t (int)
-        llgtr   %r3,%r3                 # struct compat_timespec *
-        jg      compat_sys_clock_getres
-
-ENTRY(sys32_clock_nanosleep_wrapper)
-        lgfr    %r2,%r2                 # clockid_t (int)
-        lgfr    %r3,%r3                 # int
-        llgtr   %r4,%r4                 # struct compat_timespec *
-        llgtr   %r5,%r5                 # struct compat_timespec *
-        jg      compat_sys_clock_nanosleep
-
-ENTRY(sys32_timer_create_wrapper)
-        lgfr    %r2,%r2                 # timer_t (int)
-        llgtr   %r3,%r3                 # struct compat_sigevent *
-        llgtr   %r4,%r4                 # timer_t *
-        jg      compat_sys_timer_create
-
-ENTRY(sys32_timer_settime_wrapper)
-        lgfr    %r2,%r2                 # timer_t (int)
-        lgfr    %r3,%r3                 # int
-        llgtr   %r4,%r4                 # struct compat_itimerspec *
-        llgtr   %r5,%r5                 # struct compat_itimerspec *
-        jg      compat_sys_timer_settime
-
-ENTRY(sys32_timer_gettime_wrapper)
-        lgfr    %r2,%r2                 # timer_t (int)
-        llgtr   %r3,%r3                 # struct compat_itimerspec *
-        jg      compat_sys_timer_gettime
-
-ENTRY(sys32_timer_getoverrun_wrapper)
-        lgfr    %r2,%r2                 # timer_t (int)
-        jg      sys_timer_getoverrun
-
-ENTRY(sys32_timer_delete_wrapper)
-        lgfr    %r2,%r2                 # timer_t (int)
-        jg      sys_timer_delete
-
-ENTRY(sys32_io_setup_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # u32 *
-        jg      compat_sys_io_setup
-
-ENTRY(sys32_io_destroy_wrapper)
-        llgfr   %r2,%r2                 # (aio_context_t) u32
-        jg      sys_io_destroy
-
-ENTRY(sys32_io_getevents_wrapper)
-        llgfr   %r2,%r2                 # (aio_context_t) u32
-        lgfr    %r3,%r3                 # long
-        lgfr    %r4,%r4                 # long
-        llgtr   %r5,%r5                 # struct io_event *
-        llgtr   %r6,%r6                 # struct compat_timespec *
-        jg      compat_sys_io_getevents
-
-ENTRY(sys32_io_submit_wrapper)
-        llgfr   %r2,%r2                 # (aio_context_t) u32
-        lgfr    %r3,%r3                 # long
-        llgtr   %r4,%r4                 # struct iocb **
-        jg      compat_sys_io_submit
-
-ENTRY(sys32_io_cancel_wrapper)
-        llgfr   %r2,%r2                 # (aio_context_t) u32
-        llgtr   %r3,%r3                 # struct iocb *
-        llgtr   %r4,%r4                 # struct io_event *
-        jg      sys_io_cancel
-
-ENTRY(compat_sys_statfs64_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgfr   %r3,%r3                 # compat_size_t
-        llgtr   %r4,%r4                 # struct compat_statfs64 *
-        jg      compat_sys_statfs64
-
-ENTRY(compat_sys_fstatfs64_wrapper)
-        llgfr   %r2,%r2                 # unsigned int fd
-        llgfr   %r3,%r3                 # compat_size_t
-        llgtr   %r4,%r4                 # struct compat_statfs64 *
-        jg      compat_sys_fstatfs64
-
-ENTRY(compat_sys_mq_open_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        lgfr    %r3,%r3                 # int
-        llgfr   %r4,%r4                 # mode_t
-        llgtr   %r5,%r5                 # struct compat_mq_attr *
-        jg      compat_sys_mq_open
-
-ENTRY(sys32_mq_unlink_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        jg      sys_mq_unlink
-
-ENTRY(compat_sys_mq_timedsend_wrapper)
-        lgfr    %r2,%r2                 # mqd_t
-        llgtr   %r3,%r3                 # const char *
-        llgfr   %r4,%r4                 # size_t
-        llgfr   %r5,%r5                 # unsigned int
-        llgtr   %r6,%r6                 # const struct compat_timespec *
-        jg      compat_sys_mq_timedsend
-
-ENTRY(compat_sys_mq_timedreceive_wrapper)
-        lgfr    %r2,%r2                 # mqd_t
-        llgtr   %r3,%r3                 # char *
-        llgfr   %r4,%r4                 # size_t
-        llgtr   %r5,%r5                 # unsigned int *
-        llgtr   %r6,%r6                 # const struct compat_timespec *
-        jg      compat_sys_mq_timedreceive
-
-ENTRY(compat_sys_mq_notify_wrapper)
-        lgfr    %r2,%r2                 # mqd_t
-        llgtr   %r3,%r3                 # struct compat_sigevent *
-        jg      compat_sys_mq_notify
-
-ENTRY(compat_sys_mq_getsetattr_wrapper)
-        lgfr    %r2,%r2                 # mqd_t
-        llgtr   %r3,%r3                 # struct compat_mq_attr *
-        llgtr   %r4,%r4                 # struct compat_mq_attr *
-        jg      compat_sys_mq_getsetattr
-
-ENTRY(compat_sys_add_key_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgtr   %r3,%r3                 # const char *
-        llgtr   %r4,%r4                 # const void *
-        llgfr   %r5,%r5                 # size_t
-        llgfr   %r6,%r6                 # (key_serial_t) u32
-        jg      sys_add_key
-
-ENTRY(compat_sys_request_key_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        llgtr   %r3,%r3                 # const char *
-        llgtr   %r4,%r4                 # const void *
-        llgfr   %r5,%r5                 # (key_serial_t) u32
-        jg      sys_request_key
-
-ENTRY(sys32_remap_file_pages_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # unsigned long
-        llgfr   %r4,%r4                 # unsigned long
-        llgfr   %r5,%r5                 # unsigned long
-        llgfr   %r6,%r6                 # unsigned long
-        jg      sys_remap_file_pages
-
-ENTRY(compat_sys_kexec_load_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # unsigned long
-        llgtr   %r4,%r4                 # struct kexec_segment *
-        llgfr   %r5,%r5                 # unsigned long
-        jg      compat_sys_kexec_load
-
-ENTRY(sys_ioprio_set_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        lgfr    %r4,%r4                 # int
-        jg      sys_ioprio_set
-
-ENTRY(sys_ioprio_get_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        jg      sys_ioprio_get
-
-ENTRY(sys_inotify_add_watch_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        llgfr   %r4,%r4                 # u32
-        jg      sys_inotify_add_watch
-
-ENTRY(sys_inotify_rm_watch_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgfr   %r3,%r3                 # u32
-        jg      sys_inotify_rm_watch
-
-ENTRY(sys_mkdirat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        lgfr    %r4,%r4                 # int
-        jg      sys_mkdirat
-
-ENTRY(sys_mknodat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        lgfr    %r4,%r4                 # int
-        llgfr   %r5,%r5                 # unsigned int
-        jg      sys_mknodat
-
-ENTRY(sys_fchownat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        llgfr   %r4,%r4                 # uid_t
-        llgfr   %r5,%r5                 # gid_t
-        lgfr    %r6,%r6                 # int
-        jg      sys_fchownat
-
-ENTRY(compat_sys_futimesat_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # struct timeval *
-        jg      compat_sys_futimesat
-
-ENTRY(sys32_fstatat64_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # struct stat64 *
-        lgfr    %r5,%r5                 # int
-        jg      sys32_fstatat64
-
-ENTRY(sys_unlinkat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        lgfr    %r4,%r4                 # int
-        jg      sys_unlinkat
-
-ENTRY(sys_renameat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        lgfr    %r4,%r4                 # int
-        llgtr   %r5,%r5                 # const char *
-        jg      sys_renameat
-
-ENTRY(sys_linkat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        lgfr    %r4,%r4                 # int
-        llgtr   %r5,%r5                 # const char *
-        lgfr    %r6,%r6                 # int
-        jg      sys_linkat
-
-ENTRY(sys_symlinkat_wrapper)
-        llgtr   %r2,%r2                 # const char *
-        lgfr    %r3,%r3                 # int
-        llgtr   %r4,%r4                 # const char *
-        jg      sys_symlinkat
-
-ENTRY(sys_readlinkat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        llgtr   %r4,%r4                 # char *
-        lgfr    %r5,%r5                 # int
-        jg      sys_readlinkat
-
-ENTRY(sys_fchmodat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        llgfr   %r4,%r4                 # mode_t
-        jg      sys_fchmodat
-
-ENTRY(sys_faccessat_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char *
-        lgfr    %r4,%r4                 # int
-        jg      sys_faccessat
-
-ENTRY(compat_sys_pselect6_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # fd_set *
-        llgtr   %r4,%r4                 # fd_set *
-        llgtr   %r5,%r5                 # fd_set *
-        llgtr   %r6,%r6                 # struct timespec *
-        llgt    %r0,164(%r15)           # void *
-        stg     %r0,160(%r15)
-        jg      compat_sys_pselect6
-
-ENTRY(compat_sys_ppoll_wrapper)
-        llgtr   %r2,%r2                 # struct pollfd *
-        llgfr   %r3,%r3                 # unsigned int
-        llgtr   %r4,%r4                 # struct timespec *
-        llgtr   %r5,%r5                 # const sigset_t *
-        llgfr   %r6,%r6                 # size_t
-        jg      compat_sys_ppoll
-
-ENTRY(sys_unshare_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        jg      sys_unshare
-
-ENTRY(sys_splice_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # loff_t *
-        lgfr    %r4,%r4                 # int
-        llgtr   %r5,%r5                 # loff_t *
-        llgfr   %r6,%r6                 # size_t
-        llgf    %r0,164(%r15)           # unsigned int
-        stg     %r0,160(%r15)
-        jg      sys_splice
-
-ENTRY(sys_sync_file_range_wrapper)
-        lgfr    %r2,%r2                 # int
-        sllg    %r3,%r3,32              # get high word of 64bit loff_t
-        or      %r3,%r4                 # get low word of 64bit loff_t
-        sllg    %r4,%r5,32              # get high word of 64bit loff_t
-        or      %r4,%r6                 # get low word of 64bit loff_t
-        llgf    %r5,164(%r15)           # unsigned int
-        jg      sys_sync_file_range
-
-ENTRY(sys_tee_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        llgfr   %r4,%r4                 # size_t
-        llgfr   %r5,%r5                 # unsigned int
-        jg      sys_tee
-
-ENTRY(sys_getcpu_wrapper)
-        llgtr   %r2,%r2                 # unsigned *
-        llgtr   %r3,%r3                 # unsigned *
-        llgtr   %r4,%r4                 # struct getcpu_cache *
-        jg      sys_getcpu
-
-ENTRY(compat_sys_utimes_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # struct compat_timeval *
-        jg      compat_sys_utimes
-
-ENTRY(compat_sys_utimensat_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgtr   %r3,%r3                 # char *
-        llgtr   %r4,%r4                 # struct compat_timespec *
-        lgfr    %r5,%r5                 # int
-        jg      compat_sys_utimensat
-
-ENTRY(sys_eventfd_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        jg      sys_eventfd
-
-ENTRY(sys_fallocate_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        sllg    %r4,%r4,32              # get high word of 64bit loff_t
-        lr      %r4,%r5                 # get low word of 64bit loff_t
-        sllg    %r5,%r6,32              # get high word of 64bit loff_t
-        l       %r5,164(%r15)           # get low word of 64bit loff_t
-        jg      sys_fallocate
-
-ENTRY(sys_timerfd_create_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        jg      sys_timerfd_create
-
-ENTRY(sys_eventfd2_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        lgfr    %r3,%r3                 # int
-        jg      sys_eventfd2
-
-ENTRY(sys_inotify_init1_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_inotify_init1
-
-ENTRY(sys_pipe2_wrapper)
-        llgtr   %r2,%r2                 # u32 *
-        lgfr    %r3,%r3                 # int
-        jg      sys_pipe2               # branch to system call
-
-ENTRY(sys_dup3_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned int
-        lgfr    %r4,%r4                 # int
-        jg      sys_dup3                # branch to system call
-
-ENTRY(sys_epoll_create1_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_epoll_create1       # branch to system call
-
-ENTRY(sys32_readahead_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgfr   %r3,%r3                 # u32
-        llgfr   %r4,%r4                 # u32
-        lgfr    %r5,%r5                 # s32
-        jg      sys32_readahead         # branch to system call
-
-ENTRY(sys_tkill_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        lgfr    %r3,%r3                 # int
-        jg      sys_tkill               # branch to system call
-
-ENTRY(sys_tgkill_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        lgfr    %r3,%r3                 # pid_t
-        lgfr    %r4,%r4                 # int
-        jg      sys_tgkill              # branch to system call
-
-ENTRY(compat_sys_keyctl_wrapper)
-        llgfr   %r2,%r2                 # u32
-        llgfr   %r3,%r3                 # u32
-        llgfr   %r4,%r4                 # u32
-        llgfr   %r5,%r5                 # u32
-        llgfr   %r6,%r6                 # u32
-        jg      compat_sys_keyctl       # branch to system call
-
-ENTRY(sys_perf_event_open_wrapper)
-        llgtr   %r2,%r2                 # const struct perf_event_attr *
-        lgfr    %r3,%r3                 # pid_t
-        lgfr    %r4,%r4                 # int
-        lgfr    %r5,%r5                 # int
-        llgfr   %r6,%r6                 # unsigned long
-        jg      sys_perf_event_open     # branch to system call
-
-ENTRY(sys_clone_wrapper)
-        llgfr   %r2,%r2                 # unsigned long
-        llgfr   %r3,%r3                 # unsigned long
-        llgtr   %r4,%r4                 # int *
-        llgtr   %r5,%r5                 # int *
-        jg      sys_clone               # branch to system call
-
-ENTRY(sys32_execve_wrapper)
-        llgtr   %r2,%r2                 # char *
-        llgtr   %r3,%r3                 # compat_uptr_t *
-        llgtr   %r4,%r4                 # compat_uptr_t *
-        jg      compat_sys_execve       # branch to system call
-
-ENTRY(sys_fanotify_init_wrapper)
-        llgfr   %r2,%r2                 # unsigned int
-        llgfr   %r3,%r3                 # unsigned int
-        jg      sys_fanotify_init       # branch to system call
-
-ENTRY(sys_prlimit64_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        llgfr   %r3,%r3                 # unsigned int
-        llgtr   %r4,%r4                 # const struct rlimit64 __user *
-        llgtr   %r5,%r5                 # struct rlimit64 __user *
-        jg      sys_prlimit64           # branch to system call
-
-ENTRY(sys_name_to_handle_at_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char __user *
-        llgtr   %r4,%r4                 # struct file_handle __user *
-        llgtr   %r5,%r5                 # int __user *
-        lgfr    %r6,%r6                 # int
-        jg      sys_name_to_handle_at
-
-ENTRY(compat_sys_clock_adjtime_wrapper)
-        lgfr    %r2,%r2                 # clockid_t (int)
-        llgtr   %r3,%r3                 # struct compat_timex __user *
-        jg      compat_sys_clock_adjtime
-
-ENTRY(sys_syncfs_wrapper)
-        lgfr    %r2,%r2                 # int
-        jg      sys_syncfs
-
-ENTRY(sys_setns_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        jg      sys_setns
-
-ENTRY(compat_sys_process_vm_readv_wrapper)
-        lgfr    %r2,%r2                 # compat_pid_t
-        llgtr   %r3,%r3                 # struct compat_iovec __user *
-        llgfr   %r4,%r4                 # unsigned long
-        llgtr   %r5,%r5                 # struct compat_iovec __user *
-        llgfr   %r6,%r6                 # unsigned long
-        llgf    %r0,164(%r15)           # unsigned long
-        stg     %r0,160(%r15)
-        jg      compat_sys_process_vm_readv
-
-ENTRY(compat_sys_process_vm_writev_wrapper)
-        lgfr    %r2,%r2                 # compat_pid_t
-        llgtr   %r3,%r3                 # struct compat_iovec __user *
-        llgfr   %r4,%r4                 # unsigned long
-        llgtr   %r5,%r5                 # struct compat_iovec __user *
-        llgfr   %r6,%r6                 # unsigned long
-        llgf    %r0,164(%r15)           # unsigned long
-        stg     %r0,160(%r15)
-        jg      compat_sys_process_vm_writev
-
-ENTRY(sys_s390_runtime_instr_wrapper)
-        lgfr    %r2,%r2                 # int
-        lgfr    %r3,%r3                 # int
-        jg      sys_s390_runtime_instr
-
-ENTRY(sys_kcmp_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        lgfr    %r3,%r3                 # pid_t
-        lgfr    %r4,%r4                 # int
-        llgfr   %r5,%r5                 # unsigned long
-        llgfr   %r6,%r6                 # unsigned long
-        jg      sys_kcmp
-
-ENTRY(sys_finit_module_wrapper)
-        lgfr    %r2,%r2                 # int
-        llgtr   %r3,%r3                 # const char __user *
-        lgfr    %r4,%r4                 # int
-        jg      sys_finit_module
-
-ENTRY(sys_sched_setattr_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        llgtr   %r3,%r3                 # struct sched_attr __user *
-        jg      sys_sched_setattr
-
-ENTRY(sys_sched_getattr_wrapper)
-        lgfr    %r2,%r2                 # pid_t
-        llgtr   %r3,%r3                 # const char __user *
-        llgfr   %r3,%r3                 # unsigned int
-        jg      sys_sched_getattr
diff --git a/arch/s390/kernel/compat_wrapper.c b/arch/s390/kernel/compat_wrapper.c
new file mode 100644
index 000000000000..824c39dfddfc
--- /dev/null
+++ b/arch/s390/kernel/compat_wrapper.c
@@ -0,0 +1,215 @@
+/*
+ *  Compat sytem call wrappers.
+ *
+ *    Copyright IBM Corp. 2014
+ */
+
+#include <linux/syscalls.h>
+#include <linux/compat.h>
+#include "entry.h"
+
+#define COMPAT_SYSCALL_WRAP1(name, ...) \
+        COMPAT_SYSCALL_WRAPx(1, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP2(name, ...) \
+        COMPAT_SYSCALL_WRAPx(2, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP3(name, ...) \
+        COMPAT_SYSCALL_WRAPx(3, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP4(name, ...) \
+        COMPAT_SYSCALL_WRAPx(4, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP5(name, ...) \
+        COMPAT_SYSCALL_WRAPx(5, _##name, __VA_ARGS__)
+#define COMPAT_SYSCALL_WRAP6(name, ...) \
+        COMPAT_SYSCALL_WRAPx(6, _##name, __VA_ARGS__)
+
+#define __SC_COMPAT_TYPE(t, a) \
+        __typeof(__builtin_choose_expr(sizeof(t) > 4, 0L, (t)0)) a
+
+#define __SC_COMPAT_CAST(t, a)                                          \
+({                                                                      \
+        long __ReS = a;                                                 \
+                                                                        \
+        BUILD_BUG_ON((sizeof(t) > 4) && !__TYPE_IS_L(t) &&              \
+                     !__TYPE_IS_UL(t) && !__TYPE_IS_PTR(t));            \
+        if (__TYPE_IS_L(t))                                             \
+                __ReS = (s32)a;                                         \
+        if (__TYPE_IS_UL(t))                                            \
+                __ReS = (u32)a;                                         \
+        if (__TYPE_IS_PTR(t))                                           \
+                __ReS = a & 0x7fffffff;                                 \
+        (t)__ReS;                                                       \
+})
+
+/*
+ * The COMPAT_SYSCALL_WRAP macro generates system call wrappers to be used by
+ * compat tasks. These wrappers will only be used for system calls where only
+ * the system call arguments need sign or zero extension or zeroing of the upper
+ * 33 bits of pointers.
+ * Note: since the wrapper function will afterwards call a system call which
+ * again performs zero and sign extension for all system call arguments with
+ * a size of less than eight bytes, these compat wrappers only touch those
+ * system call arguments with a size of eight bytes ((unsigned) long and
+ * pointers). Zero and sign extension for e.g. int parameters will be done by
+ * the regular system call wrappers.
+ */
+#define COMPAT_SYSCALL_WRAPx(x, name, ...)                                      \
+        asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));              \
+        asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__));\
+        asmlinkage long compat_sys##name(__MAP(x,__SC_COMPAT_TYPE,__VA_ARGS__)) \
+        {                                                                       \
+                return sys##name(__MAP(x,__SC_COMPAT_CAST,__VA_ARGS__));        \
+        }
+
+COMPAT_SYSCALL_WRAP1(exit, int, error_code);
+COMPAT_SYSCALL_WRAP1(close, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(creat, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP2(link, const char __user *, oldname, const char __user *, newname);
+COMPAT_SYSCALL_WRAP1(unlink, const char __user *, pathname);
+COMPAT_SYSCALL_WRAP1(chdir, const char __user *, filename);
+COMPAT_SYSCALL_WRAP3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev);
+COMPAT_SYSCALL_WRAP2(chmod, const char __user *, filename, umode_t, mode);
+COMPAT_SYSCALL_WRAP1(oldumount, char __user *, name);
+COMPAT_SYSCALL_WRAP1(alarm, unsigned int, seconds);
+COMPAT_SYSCALL_WRAP2(access, const char __user *, filename, int, mode);
+COMPAT_SYSCALL_WRAP1(nice, int, increment);
+COMPAT_SYSCALL_WRAP2(kill, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP2(rename, const char __user *, oldname, const char __user *, newname);
+COMPAT_SYSCALL_WRAP2(mkdir, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP1(rmdir, const char __user *, pathname);
+COMPAT_SYSCALL_WRAP1(dup, unsigned int, fildes);
+COMPAT_SYSCALL_WRAP1(pipe, int __user *, fildes);
+COMPAT_SYSCALL_WRAP1(brk, unsigned long, brk);
+COMPAT_SYSCALL_WRAP2(signal, int, sig, __sighandler_t, handler);
+COMPAT_SYSCALL_WRAP1(acct, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(umount, char __user *, name, int, flags);
+COMPAT_SYSCALL_WRAP2(setpgid, pid_t, pid, pid_t, pgid);
+COMPAT_SYSCALL_WRAP1(umask, int, mask);
+COMPAT_SYSCALL_WRAP1(chroot, const char __user *, filename);
+COMPAT_SYSCALL_WRAP2(dup2, unsigned int, oldfd, unsigned int, newfd);
+COMPAT_SYSCALL_WRAP3(sigsuspend, int, unused1, int, unused2, old_sigset_t, mask);
+COMPAT_SYSCALL_WRAP2(sethostname, char __user *, name, int, len);
+COMPAT_SYSCALL_WRAP2(symlink, const char __user *, old, const char __user *, new);
+COMPAT_SYSCALL_WRAP3(readlink, const char __user *, path, char __user *, buf, int, bufsiz);
+COMPAT_SYSCALL_WRAP1(uselib, const char __user *, library);
+COMPAT_SYSCALL_WRAP2(swapon, const char __user *, specialfile, int, swap_flags);
+COMPAT_SYSCALL_WRAP4(reboot, int, magic1, int, magic2, unsigned int, cmd, void __user *, arg);
+COMPAT_SYSCALL_WRAP2(munmap, unsigned long, addr, size_t, len);
+COMPAT_SYSCALL_WRAP2(fchmod, unsigned int, fd, umode_t, mode);
+COMPAT_SYSCALL_WRAP2(getpriority, int, which, int, who);
+COMPAT_SYSCALL_WRAP3(setpriority, int, which, int, who, int, niceval);
+COMPAT_SYSCALL_WRAP3(syslog, int, type, char __user *, buf, int, len);
+COMPAT_SYSCALL_WRAP1(swapoff, const char __user *, specialfile);
+COMPAT_SYSCALL_WRAP1(fsync, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(setdomainname, char __user *, name, int, len);
+COMPAT_SYSCALL_WRAP1(newuname, struct new_utsname __user *, name);
+COMPAT_SYSCALL_WRAP3(mprotect, unsigned long, start, size_t, len, unsigned long, prot);
+COMPAT_SYSCALL_WRAP3(init_module, void __user *, umod, unsigned long, len, const char __user *, uargs);
+COMPAT_SYSCALL_WRAP2(delete_module, const char __user *, name_user, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(quotactl, unsigned int, cmd, const char __user *, special, qid_t, id, void __user *, addr);
+COMPAT_SYSCALL_WRAP1(getpgid, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(fchdir, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(bdflush, int, func, long, data);
+COMPAT_SYSCALL_WRAP3(sysfs, int, option, unsigned long, arg1, unsigned long, arg2);
+COMPAT_SYSCALL_WRAP1(s390_personality, unsigned int, personality);
+COMPAT_SYSCALL_WRAP5(llseek, unsigned int, fd, unsigned long, high, unsigned long, low, loff_t __user *, result, unsigned int, whence);
+COMPAT_SYSCALL_WRAP2(flock, unsigned int, fd, unsigned int, cmd);
+COMPAT_SYSCALL_WRAP3(msync, unsigned long, start, size_t, len, int, flags);
+COMPAT_SYSCALL_WRAP1(getsid, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(fdatasync, unsigned int, fd);
+COMPAT_SYSCALL_WRAP2(mlock, unsigned long, start, size_t, len);
+COMPAT_SYSCALL_WRAP2(munlock, unsigned long, start, size_t, len);
+COMPAT_SYSCALL_WRAP1(mlockall, int, flags);
+COMPAT_SYSCALL_WRAP2(sched_setparam, pid_t, pid, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP2(sched_getparam, pid_t, pid, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param);
+COMPAT_SYSCALL_WRAP1(sched_getscheduler, pid_t, pid);
+COMPAT_SYSCALL_WRAP1(sched_get_priority_max, int, policy);
+COMPAT_SYSCALL_WRAP1(sched_get_priority_min, int, policy);
+COMPAT_SYSCALL_WRAP5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long, new_len, unsigned long, flags, unsigned long, new_addr);
+COMPAT_SYSCALL_WRAP3(poll, struct pollfd __user *, ufds, unsigned int, nfds, int, timeout);
+COMPAT_SYSCALL_WRAP5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5);
+COMPAT_SYSCALL_WRAP2(getcwd, char __user *, buf, unsigned long, size);
+COMPAT_SYSCALL_WRAP2(capget, cap_user_header_t, header, cap_user_data_t, dataptr);
+COMPAT_SYSCALL_WRAP2(capset, cap_user_header_t, header, const cap_user_data_t, data);
+COMPAT_SYSCALL_WRAP3(lchown, const char __user *, filename, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP2(setreuid, uid_t, ruid, uid_t, euid);
+COMPAT_SYSCALL_WRAP2(setregid, gid_t, rgid, gid_t, egid);
+COMPAT_SYSCALL_WRAP2(getgroups, int, gidsetsize, gid_t __user *, grouplist);
+COMPAT_SYSCALL_WRAP2(setgroups, int, gidsetsize, gid_t __user *, grouplist);
+COMPAT_SYSCALL_WRAP3(fchown, unsigned int, fd, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid);
+COMPAT_SYSCALL_WRAP3(getresuid, uid_t __user *, ruid, uid_t __user *, euid, uid_t __user *, suid);
+COMPAT_SYSCALL_WRAP3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid);
+COMPAT_SYSCALL_WRAP3(getresgid, gid_t __user *, rgid, gid_t __user *, egid, gid_t __user *, sgid);
+COMPAT_SYSCALL_WRAP3(chown, const char __user *, filename, uid_t, user, gid_t, group);
+COMPAT_SYSCALL_WRAP1(setuid, uid_t, uid);
+COMPAT_SYSCALL_WRAP1(setgid, gid_t, gid);
+COMPAT_SYSCALL_WRAP1(setfsuid, uid_t, uid);
+COMPAT_SYSCALL_WRAP1(setfsgid, gid_t, gid);
+COMPAT_SYSCALL_WRAP2(pivot_root, const char __user *, new_root, const char __user *, put_old);
+COMPAT_SYSCALL_WRAP3(mincore, unsigned long, start, size_t, len, unsigned char __user *, vec);
+COMPAT_SYSCALL_WRAP3(madvise, unsigned long, start, size_t, len, int, behavior);
+COMPAT_SYSCALL_WRAP5(setxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP5(lsetxattr, const char __user *, path, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP5(fsetxattr, int, fd, const char __user *, name, const void __user *, value, size_t, size, int, flags);
+COMPAT_SYSCALL_WRAP3(getdents64, unsigned int, fd, struct linux_dirent64 __user *, dirent, unsigned int, count);
+COMPAT_SYSCALL_WRAP4(getxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP4(lgetxattr, const char __user *, path, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP4(fgetxattr, int, fd, const char __user *, name, void __user *, value, size_t, size);
+COMPAT_SYSCALL_WRAP3(listxattr, const char __user *, path, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP3(llistxattr, const char __user *, path, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP3(flistxattr, int, fd, char __user *, list, size_t, size);
+COMPAT_SYSCALL_WRAP2(removexattr, const char __user *, path, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(lremovexattr, const char __user *, path, const char __user *, name);
+COMPAT_SYSCALL_WRAP2(fremovexattr, int, fd, const char __user *, name);
+COMPAT_SYSCALL_WRAP1(exit_group, int, error_code);
+COMPAT_SYSCALL_WRAP1(set_tid_address, int __user *, tidptr);
+COMPAT_SYSCALL_WRAP1(epoll_create, int, size);
+COMPAT_SYSCALL_WRAP4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event);
+COMPAT_SYSCALL_WRAP4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout);
+COMPAT_SYSCALL_WRAP1(timer_getoverrun, timer_t, timer_id);
+COMPAT_SYSCALL_WRAP1(timer_delete, compat_timer_t, compat_timer_id);
+COMPAT_SYSCALL_WRAP1(io_destroy, aio_context_t, ctx);
+COMPAT_SYSCALL_WRAP3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result);
+COMPAT_SYSCALL_WRAP1(mq_unlink, const char __user *, name);
+COMPAT_SYSCALL_WRAP5(add_key, const char __user *, tp, const char __user *, dsc, const void __user *, pld, size_t, len, key_serial_t, id);
+COMPAT_SYSCALL_WRAP4(request_key, const char __user *, tp, const char __user *, dsc, const char __user *, info, key_serial_t, id);
+COMPAT_SYSCALL_WRAP5(remap_file_pages, unsigned long, start, unsigned long, size, unsigned long, prot, unsigned long, pgoff, unsigned long, flags);
+COMPAT_SYSCALL_WRAP3(ioprio_set, int, which, int, who, int, ioprio);
+COMPAT_SYSCALL_WRAP2(ioprio_get, int, which, int, who);
+COMPAT_SYSCALL_WRAP3(inotify_add_watch, int, fd, const char __user *, path, u32, mask);
+COMPAT_SYSCALL_WRAP2(inotify_rm_watch, int, fd, __s32, wd);
+COMPAT_SYSCALL_WRAP3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode);
+COMPAT_SYSCALL_WRAP4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned, dev);
+COMPAT_SYSCALL_WRAP5(fchownat, int, dfd, const char __user *, filename, uid_t, user, gid_t, group, int, flag);
+COMPAT_SYSCALL_WRAP3(unlinkat, int, dfd, const char __user *, pathname, int, flag);
+COMPAT_SYSCALL_WRAP4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname);
+COMPAT_SYSCALL_WRAP5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags);
+COMPAT_SYSCALL_WRAP3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname);
+COMPAT_SYSCALL_WRAP4(readlinkat, int, dfd, const char __user *, path, char __user *, buf, int, bufsiz);
+COMPAT_SYSCALL_WRAP3(fchmodat, int, dfd, const char __user *, filename, umode_t, mode);
+COMPAT_SYSCALL_WRAP3(faccessat, int, dfd, const char __user *, filename, int, mode);
+COMPAT_SYSCALL_WRAP1(unshare, unsigned long, unshare_flags);
+COMPAT_SYSCALL_WRAP6(splice, int, fd_in, loff_t __user *, off_in, int, fd_out, loff_t __user *, off_out, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags);
+COMPAT_SYSCALL_WRAP3(getcpu, unsigned __user *, cpu, unsigned __user *, node, struct getcpu_cache __user *, cache);
+COMPAT_SYSCALL_WRAP1(eventfd, unsigned int, count);
+COMPAT_SYSCALL_WRAP2(timerfd_create, int, clockid, int, flags);
+COMPAT_SYSCALL_WRAP2(eventfd2, unsigned int, count, int, flags);
+COMPAT_SYSCALL_WRAP1(inotify_init1, int, flags);
+COMPAT_SYSCALL_WRAP2(pipe2, int __user *, fildes, int, flags);
+COMPAT_SYSCALL_WRAP3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags);
+COMPAT_SYSCALL_WRAP1(epoll_create1, int, flags);
+COMPAT_SYSCALL_WRAP2(tkill, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP3(tgkill, int, tgid, int, pid, int, sig);
+COMPAT_SYSCALL_WRAP5(perf_event_open, struct perf_event_attr __user *, attr_uptr, pid_t, pid, int, cpu, int, group_fd, unsigned long, flags);
+COMPAT_SYSCALL_WRAP5(clone, unsigned long, newsp, unsigned long, clone_flags, int __user *, parent_tidptr, int __user *, child_tidptr, int, tls_val);
+COMPAT_SYSCALL_WRAP2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags);
+COMPAT_SYSCALL_WRAP4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim);
+COMPAT_SYSCALL_WRAP5(name_to_handle_at, int, dfd, const char __user *, name, struct file_handle __user *, handle, int __user *, mnt_id, int, flag);
+COMPAT_SYSCALL_WRAP1(syncfs, int, fd);
+COMPAT_SYSCALL_WRAP2(setns, int, fd, int, nstype);
+COMPAT_SYSCALL_WRAP2(s390_runtime_instr, int, command, int, signum);
+COMPAT_SYSCALL_WRAP5(kcmp, pid_t, pid1, pid_t, pid2, int, type, unsigned long, idx1, unsigned long, idx2);
+COMPAT_SYSCALL_WRAP3(finit_module, int, fd, const char __user *, uargs, int, flags);
+COMPAT_SYSCALL_WRAP3(sched_setattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, flags);
+COMPAT_SYSCALL_WRAP4(sched_getattr, pid_t, pid, struct sched_attr __user *, attr, unsigned int, size, unsigned int, flags);
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index fca20b5fe79e..6b594439cca5 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -380,8 +380,6 @@ static __init void detect_machine_facilities(void)
                 S390_lowcore.machine_flags |= MACHINE_FLAG_EDAT2;
         if (test_facility(3))
                 S390_lowcore.machine_flags |= MACHINE_FLAG_IDTE;
-        if (test_facility(27))
-                S390_lowcore.machine_flags |= MACHINE_FLAG_MVCOS;
         if (test_facility(40))
                 S390_lowcore.machine_flags |= MACHINE_FLAG_LPP;
         if (test_facility(50) && test_facility(73))
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 0dc2b6d0a1ec..526d3735ed29 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -43,6 +43,7 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
                  _TIF_MCCK_PENDING)
 _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
                  _TIF_SYSCALL_TRACEPOINT)
+_TIF_TRANSFER = (_TIF_MCCK_PENDING | _TIF_TLB_WAIT)
 
 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT
@@ -159,10 +160,12 @@ ENTRY(__switch_to)
         lctl    %c4,%c4,__TASK_pid(%r3)         # load pid to control reg. 4
         mvc     __LC_CURRENT_PID(4,%r0),__TASK_pid(%r3) # store pid of next
         l       %r15,__THREAD_ksp(%r3)          # load kernel stack of next
-        tm      __TI_flags+3(%r4),_TIF_MCCK_PENDING # machine check pending?
+        lhi     %r6,_TIF_TRANSFER               # transfer TIF bits
+        n       %r6,__TI_flags(%r4)             # isolate TIF bits
         jz      0f
-        ni      __TI_flags+3(%r4),255-_TIF_MCCK_PENDING # clear flag in prev
-        oi      __TI_flags+3(%r5),_TIF_MCCK_PENDING     # set it in next
+        o       %r6,__TI_flags(%r5)             # set TIF bits of next
+        st      %r6,__TI_flags(%r5)
+        ni      __TI_flags+3(%r4),255-_TIF_TRANSFER # clear TIF bits of prev
 0:      lm      %r6,%r15,__SF_GPRS(%r15)        # load gprs of next task
         br      %r14
 
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index cb533f78c09e..6ac78192455f 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -67,9 +67,7 @@ struct s390_mmap_arg_struct;
 struct fadvise64_64_args;
 struct old_sigaction;
 
-long sys_sigreturn(void);
-long sys_rt_sigreturn(void);
-long sys32_sigreturn(void);
-long sys32_rt_sigreturn(void);
+long sys_s390_personality(unsigned int personality);
+long sys_s390_runtime_instr(int command, int signum);
 
 #endif /* _ENTRY_H */
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 384e609b4711..e09dbe5f2901 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -48,6 +48,7 @@ _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
                  _TIF_MCCK_PENDING)
 _TIF_TRACE    = (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | \
                  _TIF_SYSCALL_TRACEPOINT)
+_TIF_TRANSFER = (_TIF_MCCK_PENDING | _TIF_TLB_WAIT)
 
 #define BASED(name) name-system_call(%r13)
 
@@ -189,10 +190,12 @@ ENTRY(__switch_to)
         lctl    %c4,%c4,__TASK_pid(%r3)         # load pid to control reg. 4
         mvc     __LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next
         lg      %r15,__THREAD_ksp(%r3)          # load kernel stack of next
-        tm      __TI_flags+7(%r4),_TIF_MCCK_PENDING # machine check pending?
+        llill   %r6,_TIF_TRANSFER               # transfer TIF bits
+        ng      %r6,__TI_flags(%r4)             # isolate TIF bits
         jz      0f
-        ni      __TI_flags+7(%r4),255-_TIF_MCCK_PENDING # clear flag in prev
-        oi      __TI_flags+7(%r5),_TIF_MCCK_PENDING     # set it in next
+        og      %r6,__TI_flags(%r5)             # set TIF bits of next
+        stg     %r6,__TI_flags(%r5)
+        ni      __TI_flags+7(%r4),255-_TIF_TRANSFER # clear TIF bits of prev
 0:      lmg     %r6,%r15,__SF_GPRS(%r15)        # load gprs of next task
         br      %r14
 
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index bb27a262c44a..a770be97db4d 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -18,6 +18,7 @@
 #include <linux/errno.h>
 #include <linux/slab.h>
 #include <linux/cpu.h>
+#include <linux/irq.h>
 #include <asm/irq_regs.h>
 #include <asm/cputime.h>
 #include <asm/lowcore.h>
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 5d2dfa31c4ef..61595c1f0a0f 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -121,7 +121,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
                                : PERF_RECORD_MISC_KERNEL;
 }
 
-void print_debug_cf(void)
+static void print_debug_cf(void)
 {
         struct cpumf_ctr_info cf_info;
         int cpu = smp_processor_id();
diff --git a/arch/s390/kernel/ptrace.c b/arch/s390/kernel/ptrace.c
index f6be6087a0e9..4ac8fafec95f 100644
--- a/arch/s390/kernel/ptrace.c
+++ b/arch/s390/kernel/ptrace.c
@@ -85,7 +85,10 @@ void update_cr_regs(struct task_struct *task)
 
         /* merge TIF_SINGLE_STEP into user specified PER registers. */
         if (test_tsk_thread_flag(task, TIF_SINGLE_STEP)) {
-                new.control |= PER_EVENT_IFETCH;
+                if (test_tsk_thread_flag(task, TIF_BLOCK_STEP))
+                        new.control |= PER_EVENT_BRANCH;
+                else
+                        new.control |= PER_EVENT_IFETCH;
 #ifdef CONFIG_64BIT
                 new.control |= PER_CONTROL_SUSPENSION;
                 new.control |= PER_EVENT_TRANSACTION_END;
@@ -107,14 +110,22 @@ void update_cr_regs(struct task_struct *task)
 
 void user_enable_single_step(struct task_struct *task)
 {
+        clear_tsk_thread_flag(task, TIF_BLOCK_STEP);
         set_tsk_thread_flag(task, TIF_SINGLE_STEP);
 }
 
 void user_disable_single_step(struct task_struct *task)
 {
+        clear_tsk_thread_flag(task, TIF_BLOCK_STEP);
         clear_tsk_thread_flag(task, TIF_SINGLE_STEP);
 }
 
+void user_enable_block_step(struct task_struct *task)
+{
+        set_tsk_thread_flag(task, TIF_SINGLE_STEP);
+        set_tsk_thread_flag(task, TIF_BLOCK_STEP);
+}
+
 /*
  * Called by kernel/ptrace.c when detaching..
  *
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 09e2f468f48b..f70f2489fa5f 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -47,7 +47,6 @@
 #include <linux/compat.h>
 
 #include <asm/ipl.h>
-#include <asm/uaccess.h>
 #include <asm/facility.h>
 #include <asm/smp.h>
 #include <asm/mmu_context.h>
@@ -65,12 +64,6 @@
 #include "entry.h"
 
 /*
- * User copy operations.
- */
-struct uaccess_ops uaccess;
-EXPORT_SYMBOL(uaccess);
-
-/*
  * Machine setup..
  */
 unsigned int console_mode = 0;
@@ -294,14 +287,6 @@ static int __init parse_vmalloc(char *arg)
 }
 early_param("vmalloc", parse_vmalloc);
 
-static int __init early_parse_user_mode(char *p)
-{
-        if (!p || strcmp(p, "primary") == 0)
-                return 0;
-        return 1;
-}
-early_param("user_mode", early_parse_user_mode);
-
 void *restart_stack __attribute__((__section__(".data")));
 
 static void __init setup_lowcore(void)
@@ -1009,8 +994,6 @@ void __init setup_arch(char **cmdline_p)
         init_mm.end_data = (unsigned long) &_edata;
         init_mm.brk = (unsigned long) &_end;
 
-        uaccess = MACHINE_HAS_MVCOS ? uaccess_mvcos : uaccess_pt;
-
         parse_early_param();
         detect_memory_layout(memory_chunk, memory_end);
         os_info_init();
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index a7125b62a9a6..8827883310dd 100644
--- a/arch/s390/kernel/smp.c
+++ b/arch/s390/kernel/smp.c
@@ -773,11 +773,11 @@ void __noreturn cpu_die(void)
 
 void __init smp_fill_possible_mask(void)
 {
-        unsigned int possible, cpu;
+        unsigned int possible, sclp, cpu;
 
-        possible = setup_possible_cpus;
-        if (!possible)
-                possible = MACHINE_IS_VM ? 64 : nr_cpu_ids;
+        sclp = sclp_get_max_cpu() ?: nr_cpu_ids;
+        possible = setup_possible_cpus ?: nr_cpu_ids;
+        possible = min(possible, sclp);
         for (cpu = 0; cpu < possible && cpu < nr_cpu_ids; cpu++)
                 set_cpu_possible(cpu, true);
 }
diff --git a/arch/s390/kernel/syscalls.S b/arch/s390/kernel/syscalls.S
index 143992152ec9..542ef488bac1 100644
--- a/arch/s390/kernel/syscalls.S
+++ b/arch/s390/kernel/syscalls.S
@@ -9,349 +9,349 @@
 #define NI_SYSCALL SYSCALL(sys_ni_syscall,sys_ni_syscall,sys_ni_syscall)
 
 NI_SYSCALL                                                      /* 0 */
-SYSCALL(sys_exit,sys_exit,sys32_exit_wrapper)
+SYSCALL(sys_exit,sys_exit,compat_sys_exit)
 SYSCALL(sys_fork,sys_fork,sys_fork)
-SYSCALL(sys_read,sys_read,sys32_read_wrapper)
-SYSCALL(sys_write,sys_write,sys32_write_wrapper)
+SYSCALL(sys_read,sys_read,compat_sys_s390_read)
+SYSCALL(sys_write,sys_write,compat_sys_s390_write)
 SYSCALL(sys_open,sys_open,compat_sys_open)                      /* 5 */
-SYSCALL(sys_close,sys_close,sys32_close_wrapper)
+SYSCALL(sys_close,sys_close,compat_sys_close)
 SYSCALL(sys_restart_syscall,sys_restart_syscall,sys_restart_syscall)
-SYSCALL(sys_creat,sys_creat,sys32_creat_wrapper)
-SYSCALL(sys_link,sys_link,sys32_link_wrapper)
-SYSCALL(sys_unlink,sys_unlink,sys32_unlink_wrapper)             /* 10 */
-SYSCALL(sys_execve,sys_execve,sys32_execve_wrapper)
-SYSCALL(sys_chdir,sys_chdir,sys32_chdir_wrapper)
-SYSCALL(sys_time,sys_ni_syscall,sys32_time_wrapper)             /* old time syscall */
-SYSCALL(sys_mknod,sys_mknod,sys32_mknod_wrapper)
-SYSCALL(sys_chmod,sys_chmod,sys32_chmod_wrapper)                /* 15 */
-SYSCALL(sys_lchown16,sys_ni_syscall,sys32_lchown16_wrapper)     /* old lchown16 syscall*/
+SYSCALL(sys_creat,sys_creat,compat_sys_creat)
+SYSCALL(sys_link,sys_link,compat_sys_link)
+SYSCALL(sys_unlink,sys_unlink,compat_sys_unlink)                /* 10 */
+SYSCALL(sys_execve,sys_execve,compat_sys_execve)
+SYSCALL(sys_chdir,sys_chdir,compat_sys_chdir)
+SYSCALL(sys_time,sys_ni_syscall,compat_sys_time)                /* old time syscall */
+SYSCALL(sys_mknod,sys_mknod,compat_sys_mknod)
+SYSCALL(sys_chmod,sys_chmod,compat_sys_chmod)                   /* 15 */
+SYSCALL(sys_lchown16,sys_ni_syscall,compat_sys_s390_lchown16)   /* old lchown16 syscall*/
 NI_SYSCALL                                                      /* old break syscall holder */
 NI_SYSCALL                                                      /* old stat syscall holder */
 SYSCALL(sys_lseek,sys_lseek,compat_sys_lseek)
 SYSCALL(sys_getpid,sys_getpid,sys_getpid)                       /* 20 */
-SYSCALL(sys_mount,sys_mount,sys32_mount_wrapper)
-SYSCALL(sys_oldumount,sys_oldumount,sys32_oldumount_wrapper)
-SYSCALL(sys_setuid16,sys_ni_syscall,sys32_setuid16_wrapper)     /* old setuid16 syscall*/
-SYSCALL(sys_getuid16,sys_ni_syscall,sys32_getuid16)             /* old getuid16 syscall*/
-SYSCALL(sys_stime,sys_ni_syscall,sys32_stime_wrapper)           /* 25 old stime syscall */
-SYSCALL(sys_ptrace,sys_ptrace,sys32_ptrace_wrapper)
-SYSCALL(sys_alarm,sys_alarm,sys32_alarm_wrapper)
+SYSCALL(sys_mount,sys_mount,compat_sys_mount)
+SYSCALL(sys_oldumount,sys_oldumount,compat_sys_oldumount)
+SYSCALL(sys_setuid16,sys_ni_syscall,compat_sys_s390_setuid16)   /* old setuid16 syscall*/
+SYSCALL(sys_getuid16,sys_ni_syscall,compat_sys_s390_getuid16)   /* old getuid16 syscall*/
+SYSCALL(sys_stime,sys_ni_syscall,compat_sys_stime)              /* 25 old stime syscall */
+SYSCALL(sys_ptrace,sys_ptrace,compat_sys_ptrace)
+SYSCALL(sys_alarm,sys_alarm,compat_sys_alarm)
 NI_SYSCALL                                                      /* old fstat syscall */
 SYSCALL(sys_pause,sys_pause,sys_pause)
-SYSCALL(sys_utime,sys_utime,compat_sys_utime_wrapper)           /* 30 */
+SYSCALL(sys_utime,sys_utime,compat_sys_utime)           /* 30 */
 NI_SYSCALL                                                      /* old stty syscall */
 NI_SYSCALL                                                      /* old gtty syscall */
-SYSCALL(sys_access,sys_access,sys32_access_wrapper)
-SYSCALL(sys_nice,sys_nice,sys32_nice_wrapper)
+SYSCALL(sys_access,sys_access,compat_sys_access)
+SYSCALL(sys_nice,sys_nice,compat_sys_nice)
 NI_SYSCALL                                                      /* 35 old ftime syscall */
 SYSCALL(sys_sync,sys_sync,sys_sync)
-SYSCALL(sys_kill,sys_kill,sys32_kill_wrapper)
-SYSCALL(sys_rename,sys_rename,sys32_rename_wrapper)
-SYSCALL(sys_mkdir,sys_mkdir,sys32_mkdir_wrapper)
-SYSCALL(sys_rmdir,sys_rmdir,sys32_rmdir_wrapper)                /* 40 */
-SYSCALL(sys_dup,sys_dup,sys32_dup_wrapper)
-SYSCALL(sys_pipe,sys_pipe,sys32_pipe_wrapper)
-SYSCALL(sys_times,sys_times,compat_sys_times_wrapper)
+SYSCALL(sys_kill,sys_kill,compat_sys_kill)
+SYSCALL(sys_rename,sys_rename,compat_sys_rename)
+SYSCALL(sys_mkdir,sys_mkdir,compat_sys_mkdir)
+SYSCALL(sys_rmdir,sys_rmdir,compat_sys_rmdir)           /* 40 */
+SYSCALL(sys_dup,sys_dup,compat_sys_dup)
+SYSCALL(sys_pipe,sys_pipe,compat_sys_pipe)
+SYSCALL(sys_times,sys_times,compat_sys_times)
 NI_SYSCALL                                                      /* old prof syscall */
-SYSCALL(sys_brk,sys_brk,sys32_brk_wrapper)                      /* 45 */
-SYSCALL(sys_setgid16,sys_ni_syscall,sys32_setgid16_wrapper)     /* old setgid16 syscall*/
-SYSCALL(sys_getgid16,sys_ni_syscall,sys32_getgid16)             /* old getgid16 syscall*/
-SYSCALL(sys_signal,sys_signal,sys32_signal_wrapper)
-SYSCALL(sys_geteuid16,sys_ni_syscall,sys32_geteuid16)           /* old geteuid16 syscall */
-SYSCALL(sys_getegid16,sys_ni_syscall,sys32_getegid16)           /* 50 old getegid16 syscall */
-SYSCALL(sys_acct,sys_acct,sys32_acct_wrapper)
-SYSCALL(sys_umount,sys_umount,sys32_umount_wrapper)
+SYSCALL(sys_brk,sys_brk,compat_sys_brk)                         /* 45 */
+SYSCALL(sys_setgid16,sys_ni_syscall,compat_sys_s390_setgid16)   /* old setgid16 syscall*/
+SYSCALL(sys_getgid16,sys_ni_syscall,compat_sys_s390_getgid16)   /* old getgid16 syscall*/
+SYSCALL(sys_signal,sys_signal,compat_sys_signal)
+SYSCALL(sys_geteuid16,sys_ni_syscall,compat_sys_s390_geteuid16) /* old geteuid16 syscall */
+SYSCALL(sys_getegid16,sys_ni_syscall,compat_sys_s390_getegid16) /* 50 old getegid16 syscall */
+SYSCALL(sys_acct,sys_acct,compat_sys_acct)
+SYSCALL(sys_umount,sys_umount,compat_sys_umount)
 NI_SYSCALL                                                      /* old lock syscall */
-SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl_wrapper)
-SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl_wrapper)           /* 55 */
+SYSCALL(sys_ioctl,sys_ioctl,compat_sys_ioctl)
+SYSCALL(sys_fcntl,sys_fcntl,compat_sys_fcntl)           /* 55 */
 NI_SYSCALL                                                      /* intel mpx syscall */
-SYSCALL(sys_setpgid,sys_setpgid,sys32_setpgid_wrapper)
+SYSCALL(sys_setpgid,sys_setpgid,compat_sys_setpgid)
 NI_SYSCALL                                                      /* old ulimit syscall */
 NI_SYSCALL                                                      /* old uname syscall */
-SYSCALL(sys_umask,sys_umask,sys32_umask_wrapper)                /* 60 */
-SYSCALL(sys_chroot,sys_chroot,sys32_chroot_wrapper)
-SYSCALL(sys_ustat,sys_ustat,sys32_ustat_wrapper)
-SYSCALL(sys_dup2,sys_dup2,sys32_dup2_wrapper)
+SYSCALL(sys_umask,sys_umask,compat_sys_umask)                   /* 60 */
+SYSCALL(sys_chroot,sys_chroot,compat_sys_chroot)
+SYSCALL(sys_ustat,sys_ustat,compat_sys_ustat)
+SYSCALL(sys_dup2,sys_dup2,compat_sys_dup2)
 SYSCALL(sys_getppid,sys_getppid,sys_getppid)
 SYSCALL(sys_getpgrp,sys_getpgrp,sys_getpgrp)                    /* 65 */
 SYSCALL(sys_setsid,sys_setsid,sys_setsid)
 SYSCALL(sys_sigaction,sys_sigaction,compat_sys_sigaction)
 NI_SYSCALL                                                      /* old sgetmask syscall*/
 NI_SYSCALL                                                      /* old ssetmask syscall*/
-SYSCALL(sys_setreuid16,sys_ni_syscall,sys32_setreuid16_wrapper) /* old setreuid16 syscall */
-SYSCALL(sys_setregid16,sys_ni_syscall,sys32_setregid16_wrapper) /* old setregid16 syscall */
-SYSCALL(sys_sigsuspend,sys_sigsuspend,sys_sigsuspend_wrapper)
-SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending_wrapper)
-SYSCALL(sys_sethostname,sys_sethostname,sys32_sethostname_wrapper)
-SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit_wrapper)       /* 75 */
-SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit_wrapper)
+SYSCALL(sys_setreuid16,sys_ni_syscall,compat_sys_s390_setreuid16) /* old setreuid16 syscall */
+SYSCALL(sys_setregid16,sys_ni_syscall,compat_sys_s390_setregid16) /* old setregid16 syscall */
+SYSCALL(sys_sigsuspend,sys_sigsuspend,compat_sys_sigsuspend)
+SYSCALL(sys_sigpending,sys_sigpending,compat_sys_sigpending)
+SYSCALL(sys_sethostname,sys_sethostname,compat_sys_sethostname)
+SYSCALL(sys_setrlimit,sys_setrlimit,compat_sys_setrlimit)       /* 75 */
+SYSCALL(sys_old_getrlimit,sys_getrlimit,compat_sys_old_getrlimit)
 SYSCALL(sys_getrusage,sys_getrusage,compat_sys_getrusage)
-SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday_wrapper)
-SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday_wrapper)
-SYSCALL(sys_getgroups16,sys_ni_syscall,sys32_getgroups16_wrapper)       /* 80 old getgroups16 syscall */
-SYSCALL(sys_setgroups16,sys_ni_syscall,sys32_setgroups16_wrapper)       /* old setgroups16 syscall */
+SYSCALL(sys_gettimeofday,sys_gettimeofday,compat_sys_gettimeofday)
+SYSCALL(sys_settimeofday,sys_settimeofday,compat_sys_settimeofday)
+SYSCALL(sys_getgroups16,sys_ni_syscall,compat_sys_s390_getgroups16)     /* 80 old getgroups16 syscall */
+SYSCALL(sys_setgroups16,sys_ni_syscall,compat_sys_s390_setgroups16)     /* old setgroups16 syscall */
 NI_SYSCALL                                                      /* old select syscall */
-SYSCALL(sys_symlink,sys_symlink,sys32_symlink_wrapper)
+SYSCALL(sys_symlink,sys_symlink,compat_sys_symlink)
 NI_SYSCALL                                                      /* old lstat syscall */
-SYSCALL(sys_readlink,sys_readlink,sys32_readlink_wrapper)       /* 85 */
-SYSCALL(sys_uselib,sys_uselib,sys32_uselib_wrapper)
-SYSCALL(sys_swapon,sys_swapon,sys32_swapon_wrapper)
-SYSCALL(sys_reboot,sys_reboot,sys32_reboot_wrapper)
-SYSCALL(sys_ni_syscall,sys_ni_syscall,old32_readdir_wrapper)    /* old readdir syscall */
-SYSCALL(sys_old_mmap,sys_old_mmap,old32_mmap_wrapper)           /* 90 */
-SYSCALL(sys_munmap,sys_munmap,sys32_munmap_wrapper)
+SYSCALL(sys_readlink,sys_readlink,compat_sys_readlink)          /* 85 */
+SYSCALL(sys_uselib,sys_uselib,compat_sys_uselib)
+SYSCALL(sys_swapon,sys_swapon,compat_sys_swapon)
+SYSCALL(sys_reboot,sys_reboot,compat_sys_reboot)
+SYSCALL(sys_ni_syscall,sys_ni_syscall,compat_sys_old_readdir)   /* old readdir syscall */
+SYSCALL(sys_old_mmap,sys_old_mmap,compat_sys_s390_old_mmap)     /* 90 */
+SYSCALL(sys_munmap,sys_munmap,compat_sys_munmap)
 SYSCALL(sys_truncate,sys_truncate,compat_sys_truncate)
 SYSCALL(sys_ftruncate,sys_ftruncate,compat_sys_ftruncate)
-SYSCALL(sys_fchmod,sys_fchmod,sys32_fchmod_wrapper)
-SYSCALL(sys_fchown16,sys_ni_syscall,sys32_fchown16_wrapper)     /* 95 old fchown16 syscall*/
-SYSCALL(sys_getpriority,sys_getpriority,sys32_getpriority_wrapper)
-SYSCALL(sys_setpriority,sys_setpriority,sys32_setpriority_wrapper)
+SYSCALL(sys_fchmod,sys_fchmod,compat_sys_fchmod)
+SYSCALL(sys_fchown16,sys_ni_syscall,compat_sys_s390_fchown16)   /* 95 old fchown16 syscall*/
+SYSCALL(sys_getpriority,sys_getpriority,compat_sys_getpriority)
+SYSCALL(sys_setpriority,sys_setpriority,compat_sys_setpriority)
 NI_SYSCALL                                                      /* old profil syscall */
-SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs_wrapper)
-SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs_wrapper)     /* 100 */
+SYSCALL(sys_statfs,sys_statfs,compat_sys_statfs)
+SYSCALL(sys_fstatfs,sys_fstatfs,compat_sys_fstatfs)     /* 100 */
 NI_SYSCALL                                                      /* ioperm for i386 */
-SYSCALL(sys_socketcall,sys_socketcall,compat_sys_socketcall_wrapper)
-SYSCALL(sys_syslog,sys_syslog,sys32_syslog_wrapper)
+SYSCALL(sys_socketcall,sys_socketcall,compat_sys_socketcall)
+SYSCALL(sys_syslog,sys_syslog,compat_sys_syslog)
 SYSCALL(sys_setitimer,sys_setitimer,compat_sys_setitimer)
 SYSCALL(sys_getitimer,sys_getitimer,compat_sys_getitimer)       /* 105 */
-SYSCALL(sys_newstat,sys_newstat,compat_sys_newstat_wrapper)
-SYSCALL(sys_newlstat,sys_newlstat,compat_sys_newlstat_wrapper)
-SYSCALL(sys_newfstat,sys_newfstat,compat_sys_newfstat_wrapper)
+SYSCALL(sys_newstat,sys_newstat,compat_sys_newstat)
+SYSCALL(sys_newlstat,sys_newlstat,compat_sys_newlstat)
+SYSCALL(sys_newfstat,sys_newfstat,compat_sys_newfstat)
 NI_SYSCALL                                                      /* old uname syscall */
 SYSCALL(sys_lookup_dcookie,sys_lookup_dcookie,compat_sys_lookup_dcookie)        /* 110 */
 SYSCALL(sys_vhangup,sys_vhangup,sys_vhangup)
 NI_SYSCALL                                                      /* old "idle" system call */
 NI_SYSCALL                                                      /* vm86old for i386 */
 SYSCALL(sys_wait4,sys_wait4,compat_sys_wait4)
-SYSCALL(sys_swapoff,sys_swapoff,sys32_swapoff_wrapper)          /* 115 */
-SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo_wrapper)
+SYSCALL(sys_swapoff,sys_swapoff,compat_sys_swapoff)             /* 115 */
+SYSCALL(sys_sysinfo,sys_sysinfo,compat_sys_sysinfo)
 SYSCALL(sys_s390_ipc,sys_s390_ipc,compat_sys_s390_ipc)
-SYSCALL(sys_fsync,sys_fsync,sys32_fsync_wrapper)
-SYSCALL(sys_sigreturn,sys_sigreturn,sys32_sigreturn)
-SYSCALL(sys_clone,sys_clone,sys_clone_wrapper)                  /* 120 */
-SYSCALL(sys_setdomainname,sys_setdomainname,sys32_setdomainname_wrapper)
-SYSCALL(sys_newuname,sys_newuname,sys32_newuname_wrapper)
+SYSCALL(sys_fsync,sys_fsync,compat_sys_fsync)
+SYSCALL(sys_sigreturn,sys_sigreturn,compat_sys_sigreturn)
+SYSCALL(sys_clone,sys_clone,compat_sys_clone)                   /* 120 */
+SYSCALL(sys_setdomainname,sys_setdomainname,compat_sys_setdomainname)
+SYSCALL(sys_newuname,sys_newuname,compat_sys_newuname)
 NI_SYSCALL                                                      /* modify_ldt for i386 */
-SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex_wrapper)
-SYSCALL(sys_mprotect,sys_mprotect,sys32_mprotect_wrapper)       /* 125 */
+SYSCALL(sys_adjtimex,sys_adjtimex,compat_sys_adjtimex)
+SYSCALL(sys_mprotect,sys_mprotect,compat_sys_mprotect)          /* 125 */
 SYSCALL(sys_sigprocmask,sys_sigprocmask,compat_sys_sigprocmask)
 NI_SYSCALL                                                      /* old "create module" */
-SYSCALL(sys_init_module,sys_init_module,sys_init_module_wrapper)
-SYSCALL(sys_delete_module,sys_delete_module,sys_delete_module_wrapper)
+SYSCALL(sys_init_module,sys_init_module,compat_sys_init_module)
+SYSCALL(sys_delete_module,sys_delete_module,compat_sys_delete_module)
 NI_SYSCALL                                                      /* 130: old get_kernel_syms */
-SYSCALL(sys_quotactl,sys_quotactl,sys32_quotactl_wrapper)
-SYSCALL(sys_getpgid,sys_getpgid,sys32_getpgid_wrapper)
-SYSCALL(sys_fchdir,sys_fchdir,sys32_fchdir_wrapper)
-SYSCALL(sys_bdflush,sys_bdflush,sys32_bdflush_wrapper)
-SYSCALL(sys_sysfs,sys_sysfs,sys32_sysfs_wrapper)                /* 135 */
-SYSCALL(sys_personality,sys_s390_personality,sys32_personality_wrapper)
+SYSCALL(sys_quotactl,sys_quotactl,compat_sys_quotactl)
+SYSCALL(sys_getpgid,sys_getpgid,compat_sys_getpgid)
+SYSCALL(sys_fchdir,sys_fchdir,compat_sys_fchdir)
+SYSCALL(sys_bdflush,sys_bdflush,compat_sys_bdflush)
+SYSCALL(sys_sysfs,sys_sysfs,compat_sys_sysfs)           /* 135 */
+SYSCALL(sys_personality,sys_s390_personality,compat_sys_s390_personality)
 NI_SYSCALL                                                      /* for afs_syscall */
-SYSCALL(sys_setfsuid16,sys_ni_syscall,sys32_setfsuid16_wrapper) /* old setfsuid16 syscall */
-SYSCALL(sys_setfsgid16,sys_ni_syscall,sys32_setfsgid16_wrapper) /* old setfsgid16 syscall */
-SYSCALL(sys_llseek,sys_llseek,sys32_llseek_wrapper)             /* 140 */
-SYSCALL(sys_getdents,sys_getdents,sys32_getdents_wrapper)
-SYSCALL(sys_select,sys_select,compat_sys_select_wrapper)
-SYSCALL(sys_flock,sys_flock,sys32_flock_wrapper)
-SYSCALL(sys_msync,sys_msync,sys32_msync_wrapper)
-SYSCALL(sys_readv,sys_readv,compat_sys_readv_wrapper)           /* 145 */
-SYSCALL(sys_writev,sys_writev,compat_sys_writev_wrapper)
-SYSCALL(sys_getsid,sys_getsid,sys32_getsid_wrapper)
-SYSCALL(sys_fdatasync,sys_fdatasync,sys32_fdatasync_wrapper)
+SYSCALL(sys_setfsuid16,sys_ni_syscall,compat_sys_s390_setfsuid16)       /* old setfsuid16 syscall */
+SYSCALL(sys_setfsgid16,sys_ni_syscall,compat_sys_s390_setfsgid16)       /* old setfsgid16 syscall */
+SYSCALL(sys_llseek,sys_llseek,compat_sys_llseek)                /* 140 */
+SYSCALL(sys_getdents,sys_getdents,compat_sys_getdents)
+SYSCALL(sys_select,sys_select,compat_sys_select)
+SYSCALL(sys_flock,sys_flock,compat_sys_flock)
+SYSCALL(sys_msync,sys_msync,compat_sys_msync)
+SYSCALL(sys_readv,sys_readv,compat_sys_readv)           /* 145 */
+SYSCALL(sys_writev,sys_writev,compat_sys_writev)
+SYSCALL(sys_getsid,sys_getsid,compat_sys_getsid)
+SYSCALL(sys_fdatasync,sys_fdatasync,compat_sys_fdatasync)
 SYSCALL(sys_sysctl,sys_sysctl,compat_sys_sysctl)
-SYSCALL(sys_mlock,sys_mlock,sys32_mlock_wrapper)                /* 150 */
-SYSCALL(sys_munlock,sys_munlock,sys32_munlock_wrapper)
-SYSCALL(sys_mlockall,sys_mlockall,sys32_mlockall_wrapper)
+SYSCALL(sys_mlock,sys_mlock,compat_sys_mlock)                   /* 150 */
+SYSCALL(sys_munlock,sys_munlock,compat_sys_munlock)
+SYSCALL(sys_mlockall,sys_mlockall,compat_sys_mlockall)
 SYSCALL(sys_munlockall,sys_munlockall,sys_munlockall)
-SYSCALL(sys_sched_setparam,sys_sched_setparam,sys32_sched_setparam_wrapper)
-SYSCALL(sys_sched_getparam,sys_sched_getparam,sys32_sched_getparam_wrapper)     /* 155 */
-SYSCALL(sys_sched_setscheduler,sys_sched_setscheduler,sys32_sched_setscheduler_wrapper)
-SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler,sys32_sched_getscheduler_wrapper)
+SYSCALL(sys_sched_setparam,sys_sched_setparam,compat_sys_sched_setparam)
+SYSCALL(sys_sched_getparam,sys_sched_getparam,compat_sys_sched_getparam)        /* 155 */
+SYSCALL(sys_sched_setscheduler,sys_sched_setscheduler,compat_sys_sched_setscheduler)
+SYSCALL(sys_sched_getscheduler,sys_sched_getscheduler,compat_sys_sched_getscheduler)
 SYSCALL(sys_sched_yield,sys_sched_yield,sys_sched_yield)
-SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max,sys32_sched_get_priority_max_wrapper)
-SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min,sys32_sched_get_priority_min_wrapper)     /* 160 */
+SYSCALL(sys_sched_get_priority_max,sys_sched_get_priority_max,compat_sys_sched_get_priority_max)
+SYSCALL(sys_sched_get_priority_min,sys_sched_get_priority_min,compat_sys_sched_get_priority_min)        /* 160 */
 SYSCALL(sys_sched_rr_get_interval,sys_sched_rr_get_interval,compat_sys_sched_rr_get_interval)
-SYSCALL(sys_nanosleep,sys_nanosleep,compat_sys_nanosleep_wrapper)
-SYSCALL(sys_mremap,sys_mremap,sys32_mremap_wrapper)
-SYSCALL(sys_setresuid16,sys_ni_syscall,sys32_setresuid16_wrapper)       /* old setresuid16 syscall */
-SYSCALL(sys_getresuid16,sys_ni_syscall,sys32_getresuid16_wrapper)       /* 165 old getresuid16 syscall */
+SYSCALL(sys_nanosleep,sys_nanosleep,compat_sys_nanosleep)
+SYSCALL(sys_mremap,sys_mremap,compat_sys_mremap)
+SYSCALL(sys_setresuid16,sys_ni_syscall,compat_sys_s390_setresuid16)     /* old setresuid16 syscall */
+SYSCALL(sys_getresuid16,sys_ni_syscall,compat_sys_s390_getresuid16)     /* 165 old getresuid16 syscall */
 NI_SYSCALL                                                      /* for vm86 */
 NI_SYSCALL                                                      /* old sys_query_module */
-SYSCALL(sys_poll,sys_poll,sys32_poll_wrapper)
+SYSCALL(sys_poll,sys_poll,compat_sys_poll)
 NI_SYSCALL                                                      /* old nfsservctl */
-SYSCALL(sys_setresgid16,sys_ni_syscall,sys32_setresgid16_wrapper)       /* 170 old setresgid16 syscall */
-SYSCALL(sys_getresgid16,sys_ni_syscall,sys32_getresgid16_wrapper)       /* old getresgid16 syscall */
-SYSCALL(sys_prctl,sys_prctl,sys32_prctl_wrapper)
-SYSCALL(sys_rt_sigreturn,sys_rt_sigreturn,sys32_rt_sigreturn)
+SYSCALL(sys_setresgid16,sys_ni_syscall,compat_sys_s390_setresgid16)     /* 170 old setresgid16 syscall */
+SYSCALL(sys_getresgid16,sys_ni_syscall,compat_sys_s390_getresgid16)     /* old getresgid16 syscall */
+SYSCALL(sys_prctl,sys_prctl,compat_sys_prctl)
+SYSCALL(sys_rt_sigreturn,sys_rt_sigreturn,compat_sys_rt_sigreturn)
 SYSCALL(sys_rt_sigaction,sys_rt_sigaction,compat_sys_rt_sigaction)
 SYSCALL(sys_rt_sigprocmask,sys_rt_sigprocmask,compat_sys_rt_sigprocmask) /* 175 */
 SYSCALL(sys_rt_sigpending,sys_rt_sigpending,compat_sys_rt_sigpending)
 SYSCALL(sys_rt_sigtimedwait,sys_rt_sigtimedwait,compat_sys_rt_sigtimedwait)
 SYSCALL(sys_rt_sigqueueinfo,sys_rt_sigqueueinfo,compat_sys_rt_sigqueueinfo)
 SYSCALL(sys_rt_sigsuspend,sys_rt_sigsuspend,compat_sys_rt_sigsuspend)
-SYSCALL(sys_pread64,sys_pread64,sys32_pread64_wrapper)          /* 180 */
-SYSCALL(sys_pwrite64,sys_pwrite64,sys32_pwrite64_wrapper)
-SYSCALL(sys_chown16,sys_ni_syscall,sys32_chown16_wrapper)       /* old chown16 syscall */
-SYSCALL(sys_getcwd,sys_getcwd,sys32_getcwd_wrapper)
-SYSCALL(sys_capget,sys_capget,sys32_capget_wrapper)
-SYSCALL(sys_capset,sys_capset,sys32_capset_wrapper)             /* 185 */
+SYSCALL(sys_pread64,sys_pread64,compat_sys_s390_pread64)                /* 180 */
+SYSCALL(sys_pwrite64,sys_pwrite64,compat_sys_s390_pwrite64)
+SYSCALL(sys_chown16,sys_ni_syscall,compat_sys_s390_chown16)     /* old chown16 syscall */
+SYSCALL(sys_getcwd,sys_getcwd,compat_sys_getcwd)
+SYSCALL(sys_capget,sys_capget,compat_sys_capget)
+SYSCALL(sys_capset,sys_capset,compat_sys_capset)                /* 185 */
 SYSCALL(sys_sigaltstack,sys_sigaltstack,compat_sys_sigaltstack)
 SYSCALL(sys_sendfile,sys_sendfile64,compat_sys_sendfile)
 NI_SYSCALL                                                      /* streams1 */
 NI_SYSCALL                                                      /* streams2 */
 SYSCALL(sys_vfork,sys_vfork,sys_vfork)                          /* 190 */
-SYSCALL(sys_getrlimit,sys_getrlimit,compat_sys_getrlimit_wrapper)
-SYSCALL(sys_mmap2,sys_mmap2,sys32_mmap2_wrapper)
-SYSCALL(sys_truncate64,sys_ni_syscall,sys32_truncate64_wrapper)
-SYSCALL(sys_ftruncate64,sys_ni_syscall,sys32_ftruncate64_wrapper)
-SYSCALL(sys_stat64,sys_ni_syscall,sys32_stat64_wrapper)         /* 195 */
-SYSCALL(sys_lstat64,sys_ni_syscall,sys32_lstat64_wrapper)
-SYSCALL(sys_fstat64,sys_ni_syscall,sys32_fstat64_wrapper)
-SYSCALL(sys_lchown,sys_lchown,sys32_lchown_wrapper)
+SYSCALL(sys_getrlimit,sys_getrlimit,compat_sys_getrlimit)
+SYSCALL(sys_mmap2,sys_mmap2,compat_sys_s390_mmap2)
+SYSCALL(sys_truncate64,sys_ni_syscall,compat_sys_s390_truncate64)
+SYSCALL(sys_ftruncate64,sys_ni_syscall,compat_sys_s390_ftruncate64)
+SYSCALL(sys_stat64,sys_ni_syscall,compat_sys_s390_stat64)               /* 195 */
+SYSCALL(sys_lstat64,sys_ni_syscall,compat_sys_s390_lstat64)
+SYSCALL(sys_fstat64,sys_ni_syscall,compat_sys_s390_fstat64)
+SYSCALL(sys_lchown,sys_lchown,compat_sys_lchown)
 SYSCALL(sys_getuid,sys_getuid,sys_getuid)
 SYSCALL(sys_getgid,sys_getgid,sys_getgid)                       /* 200 */
 SYSCALL(sys_geteuid,sys_geteuid,sys_geteuid)
 SYSCALL(sys_getegid,sys_getegid,sys_getegid)
-SYSCALL(sys_setreuid,sys_setreuid,sys32_setreuid_wrapper)
-SYSCALL(sys_setregid,sys_setregid,sys32_setregid_wrapper)
-SYSCALL(sys_getgroups,sys_getgroups,sys32_getgroups_wrapper)    /* 205 */
-SYSCALL(sys_setgroups,sys_setgroups,sys32_setgroups_wrapper)
-SYSCALL(sys_fchown,sys_fchown,sys32_fchown_wrapper)
-SYSCALL(sys_setresuid,sys_setresuid,sys32_setresuid_wrapper)
-SYSCALL(sys_getresuid,sys_getresuid,sys32_getresuid_wrapper)
-SYSCALL(sys_setresgid,sys_setresgid,sys32_setresgid_wrapper)    /* 210 */
-SYSCALL(sys_getresgid,sys_getresgid,sys32_getresgid_wrapper)
-SYSCALL(sys_chown,sys_chown,sys32_chown_wrapper)
-SYSCALL(sys_setuid,sys_setuid,sys32_setuid_wrapper)
-SYSCALL(sys_setgid,sys_setgid,sys32_setgid_wrapper)
-SYSCALL(sys_setfsuid,sys_setfsuid,sys32_setfsuid_wrapper)       /* 215 */
-SYSCALL(sys_setfsgid,sys_setfsgid,sys32_setfsgid_wrapper)
-SYSCALL(sys_pivot_root,sys_pivot_root,sys32_pivot_root_wrapper)
-SYSCALL(sys_mincore,sys_mincore,sys32_mincore_wrapper)
-SYSCALL(sys_madvise,sys_madvise,sys32_madvise_wrapper)
-SYSCALL(sys_getdents64,sys_getdents64,sys32_getdents64_wrapper) /* 220 */
-SYSCALL(sys_fcntl64,sys_ni_syscall,compat_sys_fcntl64_wrapper)
-SYSCALL(sys_readahead,sys_readahead,sys32_readahead_wrapper)
+SYSCALL(sys_setreuid,sys_setreuid,compat_sys_setreuid)
+SYSCALL(sys_setregid,sys_setregid,compat_sys_setregid)
+SYSCALL(sys_getgroups,sys_getgroups,compat_sys_getgroups)       /* 205 */
+SYSCALL(sys_setgroups,sys_setgroups,compat_sys_setgroups)
+SYSCALL(sys_fchown,sys_fchown,compat_sys_fchown)
+SYSCALL(sys_setresuid,sys_setresuid,compat_sys_setresuid)
+SYSCALL(sys_getresuid,sys_getresuid,compat_sys_getresuid)
+SYSCALL(sys_setresgid,sys_setresgid,compat_sys_setresgid)       /* 210 */
+SYSCALL(sys_getresgid,sys_getresgid,compat_sys_getresgid)
+SYSCALL(sys_chown,sys_chown,compat_sys_chown)
+SYSCALL(sys_setuid,sys_setuid,compat_sys_setuid)
+SYSCALL(sys_setgid,sys_setgid,compat_sys_setgid)
+SYSCALL(sys_setfsuid,sys_setfsuid,compat_sys_setfsuid)  /* 215 */
+SYSCALL(sys_setfsgid,sys_setfsgid,compat_sys_setfsgid)
+SYSCALL(sys_pivot_root,sys_pivot_root,compat_sys_pivot_root)
+SYSCALL(sys_mincore,sys_mincore,compat_sys_mincore)
+SYSCALL(sys_madvise,sys_madvise,compat_sys_madvise)
+SYSCALL(sys_getdents64,sys_getdents64,compat_sys_getdents64)    /* 220 */
+SYSCALL(sys_fcntl64,sys_ni_syscall,compat_sys_fcntl64)
+SYSCALL(sys_readahead,sys_readahead,compat_sys_s390_readahead)
 SYSCALL(sys_sendfile64,sys_ni_syscall,compat_sys_sendfile64)
-SYSCALL(sys_setxattr,sys_setxattr,sys32_setxattr_wrapper)
-SYSCALL(sys_lsetxattr,sys_lsetxattr,sys32_lsetxattr_wrapper)    /* 225 */
-SYSCALL(sys_fsetxattr,sys_fsetxattr,sys32_fsetxattr_wrapper)
-SYSCALL(sys_getxattr,sys_getxattr,sys32_getxattr_wrapper)
-SYSCALL(sys_lgetxattr,sys_lgetxattr,sys32_lgetxattr_wrapper)
-SYSCALL(sys_fgetxattr,sys_fgetxattr,sys32_fgetxattr_wrapper)
-SYSCALL(sys_listxattr,sys_listxattr,sys32_listxattr_wrapper)    /* 230 */
-SYSCALL(sys_llistxattr,sys_llistxattr,sys32_llistxattr_wrapper)
-SYSCALL(sys_flistxattr,sys_flistxattr,sys32_flistxattr_wrapper)
-SYSCALL(sys_removexattr,sys_removexattr,sys32_removexattr_wrapper)
-SYSCALL(sys_lremovexattr,sys_lremovexattr,sys32_lremovexattr_wrapper)
-SYSCALL(sys_fremovexattr,sys_fremovexattr,sys32_fremovexattr_wrapper)   /* 235 */
+SYSCALL(sys_setxattr,sys_setxattr,compat_sys_setxattr)
+SYSCALL(sys_lsetxattr,sys_lsetxattr,compat_sys_lsetxattr)       /* 225 */
+SYSCALL(sys_fsetxattr,sys_fsetxattr,compat_sys_fsetxattr)
+SYSCALL(sys_getxattr,sys_getxattr,compat_sys_getxattr)
+SYSCALL(sys_lgetxattr,sys_lgetxattr,compat_sys_lgetxattr)
+SYSCALL(sys_fgetxattr,sys_fgetxattr,compat_sys_fgetxattr)
+SYSCALL(sys_listxattr,sys_listxattr,compat_sys_listxattr)       /* 230 */
+SYSCALL(sys_llistxattr,sys_llistxattr,compat_sys_llistxattr)
+SYSCALL(sys_flistxattr,sys_flistxattr,compat_sys_flistxattr)
+SYSCALL(sys_removexattr,sys_removexattr,compat_sys_removexattr)
+SYSCALL(sys_lremovexattr,sys_lremovexattr,compat_sys_lremovexattr)
+SYSCALL(sys_fremovexattr,sys_fremovexattr,compat_sys_fremovexattr)      /* 235 */
 SYSCALL(sys_gettid,sys_gettid,sys_gettid)
-SYSCALL(sys_tkill,sys_tkill,sys_tkill_wrapper)
+SYSCALL(sys_tkill,sys_tkill,compat_sys_tkill)
 SYSCALL(sys_futex,sys_futex,compat_sys_futex)
-SYSCALL(sys_sched_setaffinity,sys_sched_setaffinity,sys32_sched_setaffinity_wrapper)
-SYSCALL(sys_sched_getaffinity,sys_sched_getaffinity,sys32_sched_getaffinity_wrapper)    /* 240 */
-SYSCALL(sys_tgkill,sys_tgkill,sys_tgkill_wrapper)
+SYSCALL(sys_sched_setaffinity,sys_sched_setaffinity,compat_sys_sched_setaffinity)
+SYSCALL(sys_sched_getaffinity,sys_sched_getaffinity,compat_sys_sched_getaffinity)       /* 240 */
+SYSCALL(sys_tgkill,sys_tgkill,compat_sys_tgkill)
 NI_SYSCALL                                                      /* reserved for TUX */
-SYSCALL(sys_io_setup,sys_io_setup,sys32_io_setup_wrapper)
-SYSCALL(sys_io_destroy,sys_io_destroy,sys32_io_destroy_wrapper)
-SYSCALL(sys_io_getevents,sys_io_getevents,sys32_io_getevents_wrapper)   /* 245 */
-SYSCALL(sys_io_submit,sys_io_submit,sys32_io_submit_wrapper)
-SYSCALL(sys_io_cancel,sys_io_cancel,sys32_io_cancel_wrapper)
-SYSCALL(sys_exit_group,sys_exit_group,sys32_exit_group_wrapper)
-SYSCALL(sys_epoll_create,sys_epoll_create,sys_epoll_create_wrapper)
-SYSCALL(sys_epoll_ctl,sys_epoll_ctl,sys_epoll_ctl_wrapper)      /* 250 */
-SYSCALL(sys_epoll_wait,sys_epoll_wait,sys_epoll_wait_wrapper)
-SYSCALL(sys_set_tid_address,sys_set_tid_address,sys32_set_tid_address_wrapper)
-SYSCALL(sys_s390_fadvise64,sys_fadvise64_64,sys32_fadvise64_wrapper)
-SYSCALL(sys_timer_create,sys_timer_create,sys32_timer_create_wrapper)
-SYSCALL(sys_timer_settime,sys_timer_settime,sys32_timer_settime_wrapper)        /* 255 */
-SYSCALL(sys_timer_gettime,sys_timer_gettime,sys32_timer_gettime_wrapper)
-SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun,sys32_timer_getoverrun_wrapper)
-SYSCALL(sys_timer_delete,sys_timer_delete,sys32_timer_delete_wrapper)
-SYSCALL(sys_clock_settime,sys_clock_settime,sys32_clock_settime_wrapper)
-SYSCALL(sys_clock_gettime,sys_clock_gettime,sys32_clock_gettime_wrapper)        /* 260 */
-SYSCALL(sys_clock_getres,sys_clock_getres,sys32_clock_getres_wrapper)
-SYSCALL(sys_clock_nanosleep,sys_clock_nanosleep,sys32_clock_nanosleep_wrapper)
+SYSCALL(sys_io_setup,sys_io_setup,compat_sys_io_setup)
+SYSCALL(sys_io_destroy,sys_io_destroy,compat_sys_io_destroy)
+SYSCALL(sys_io_getevents,sys_io_getevents,compat_sys_io_getevents)      /* 245 */
+SYSCALL(sys_io_submit,sys_io_submit,compat_sys_io_submit)
+SYSCALL(sys_io_cancel,sys_io_cancel,compat_sys_io_cancel)
+SYSCALL(sys_exit_group,sys_exit_group,compat_sys_exit_group)
+SYSCALL(sys_epoll_create,sys_epoll_create,compat_sys_epoll_create)
+SYSCALL(sys_epoll_ctl,sys_epoll_ctl,compat_sys_epoll_ctl)       /* 250 */
+SYSCALL(sys_epoll_wait,sys_epoll_wait,compat_sys_epoll_wait)
+SYSCALL(sys_set_tid_address,sys_set_tid_address,compat_sys_set_tid_address)
+SYSCALL(sys_s390_fadvise64,sys_fadvise64_64,compat_sys_s390_fadvise64)
+SYSCALL(sys_timer_create,sys_timer_create,compat_sys_timer_create)
+SYSCALL(sys_timer_settime,sys_timer_settime,compat_sys_timer_settime)   /* 255 */
+SYSCALL(sys_timer_gettime,sys_timer_gettime,compat_sys_timer_gettime)
+SYSCALL(sys_timer_getoverrun,sys_timer_getoverrun,compat_sys_timer_getoverrun)
+SYSCALL(sys_timer_delete,sys_timer_delete,compat_sys_timer_delete)
+SYSCALL(sys_clock_settime,sys_clock_settime,compat_sys_clock_settime)
+SYSCALL(sys_clock_gettime,sys_clock_gettime,compat_sys_clock_gettime)   /* 260 */
+SYSCALL(sys_clock_getres,sys_clock_getres,compat_sys_clock_getres)
+SYSCALL(sys_clock_nanosleep,sys_clock_nanosleep,compat_sys_clock_nanosleep)
 NI_SYSCALL                                                      /* reserved for vserver */
-SYSCALL(sys_s390_fadvise64_64,sys_ni_syscall,sys32_fadvise64_64_wrapper)
-SYSCALL(sys_statfs64,sys_statfs64,compat_sys_statfs64_wrapper)
-SYSCALL(sys_fstatfs64,sys_fstatfs64,compat_sys_fstatfs64_wrapper)
-SYSCALL(sys_remap_file_pages,sys_remap_file_pages,sys32_remap_file_pages_wrapper)
+SYSCALL(sys_s390_fadvise64_64,sys_ni_syscall,compat_sys_s390_fadvise64_64)
+SYSCALL(sys_statfs64,sys_statfs64,compat_sys_statfs64)
+SYSCALL(sys_fstatfs64,sys_fstatfs64,compat_sys_fstatfs64)
+SYSCALL(sys_remap_file_pages,sys_remap_file_pages,compat_sys_remap_file_pages)
 NI_SYSCALL                                                      /* 268 sys_mbind */
 NI_SYSCALL                                                      /* 269 sys_get_mempolicy */
 NI_SYSCALL                                                      /* 270 sys_set_mempolicy */
-SYSCALL(sys_mq_open,sys_mq_open,compat_sys_mq_open_wrapper)
-SYSCALL(sys_mq_unlink,sys_mq_unlink,sys32_mq_unlink_wrapper)
-SYSCALL(sys_mq_timedsend,sys_mq_timedsend,compat_sys_mq_timedsend_wrapper)
-SYSCALL(sys_mq_timedreceive,sys_mq_timedreceive,compat_sys_mq_timedreceive_wrapper)
-SYSCALL(sys_mq_notify,sys_mq_notify,compat_sys_mq_notify_wrapper) /* 275 */
-SYSCALL(sys_mq_getsetattr,sys_mq_getsetattr,compat_sys_mq_getsetattr_wrapper)
-SYSCALL(sys_kexec_load,sys_kexec_load,compat_sys_kexec_load_wrapper)
-SYSCALL(sys_add_key,sys_add_key,compat_sys_add_key_wrapper)
-SYSCALL(sys_request_key,sys_request_key,compat_sys_request_key_wrapper)
-SYSCALL(sys_keyctl,sys_keyctl,compat_sys_keyctl_wrapper)                /* 280 */
+SYSCALL(sys_mq_open,sys_mq_open,compat_sys_mq_open)
+SYSCALL(sys_mq_unlink,sys_mq_unlink,compat_sys_mq_unlink)
+SYSCALL(sys_mq_timedsend,sys_mq_timedsend,compat_sys_mq_timedsend)
+SYSCALL(sys_mq_timedreceive,sys_mq_timedreceive,compat_sys_mq_timedreceive)
+SYSCALL(sys_mq_notify,sys_mq_notify,compat_sys_mq_notify) /* 275 */
+SYSCALL(sys_mq_getsetattr,sys_mq_getsetattr,compat_sys_mq_getsetattr)
+SYSCALL(sys_kexec_load,sys_kexec_load,compat_sys_kexec_load)
+SYSCALL(sys_add_key,sys_add_key,compat_sys_add_key)
+SYSCALL(sys_request_key,sys_request_key,compat_sys_request_key)
+SYSCALL(sys_keyctl,sys_keyctl,compat_sys_keyctl)                /* 280 */
 SYSCALL(sys_waitid,sys_waitid,compat_sys_waitid)
-SYSCALL(sys_ioprio_set,sys_ioprio_set,sys_ioprio_set_wrapper)
-SYSCALL(sys_ioprio_get,sys_ioprio_get,sys_ioprio_get_wrapper)
+SYSCALL(sys_ioprio_set,sys_ioprio_set,compat_sys_ioprio_set)
+SYSCALL(sys_ioprio_get,sys_ioprio_get,compat_sys_ioprio_get)
 SYSCALL(sys_inotify_init,sys_inotify_init,sys_inotify_init)
-SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,sys_inotify_add_watch_wrapper)      /* 285 */
-SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,sys_inotify_rm_watch_wrapper)
+SYSCALL(sys_inotify_add_watch,sys_inotify_add_watch,compat_sys_inotify_add_watch)       /* 285 */
+SYSCALL(sys_inotify_rm_watch,sys_inotify_rm_watch,compat_sys_inotify_rm_watch)
 NI_SYSCALL                                                      /* 287 sys_migrate_pages */
 SYSCALL(sys_openat,sys_openat,compat_sys_openat)
-SYSCALL(sys_mkdirat,sys_mkdirat,sys_mkdirat_wrapper)
-SYSCALL(sys_mknodat,sys_mknodat,sys_mknodat_wrapper)    /* 290 */
-SYSCALL(sys_fchownat,sys_fchownat,sys_fchownat_wrapper)
-SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat_wrapper)
-SYSCALL(sys_fstatat64,sys_newfstatat,sys32_fstatat64_wrapper)
-SYSCALL(sys_unlinkat,sys_unlinkat,sys_unlinkat_wrapper)
-SYSCALL(sys_renameat,sys_renameat,sys_renameat_wrapper) /* 295 */
-SYSCALL(sys_linkat,sys_linkat,sys_linkat_wrapper)
-SYSCALL(sys_symlinkat,sys_symlinkat,sys_symlinkat_wrapper)
-SYSCALL(sys_readlinkat,sys_readlinkat,sys_readlinkat_wrapper)
-SYSCALL(sys_fchmodat,sys_fchmodat,sys_fchmodat_wrapper)
-SYSCALL(sys_faccessat,sys_faccessat,sys_faccessat_wrapper)      /* 300 */
-SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6_wrapper)
-SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll_wrapper)
-SYSCALL(sys_unshare,sys_unshare,sys_unshare_wrapper)
+SYSCALL(sys_mkdirat,sys_mkdirat,compat_sys_mkdirat)
+SYSCALL(sys_mknodat,sys_mknodat,compat_sys_mknodat)     /* 290 */
+SYSCALL(sys_fchownat,sys_fchownat,compat_sys_fchownat)
+SYSCALL(sys_futimesat,sys_futimesat,compat_sys_futimesat)
+SYSCALL(sys_fstatat64,sys_newfstatat,compat_sys_s390_fstatat64)
+SYSCALL(sys_unlinkat,sys_unlinkat,compat_sys_unlinkat)
+SYSCALL(sys_renameat,sys_renameat,compat_sys_renameat)  /* 295 */
+SYSCALL(sys_linkat,sys_linkat,compat_sys_linkat)
+SYSCALL(sys_symlinkat,sys_symlinkat,compat_sys_symlinkat)
+SYSCALL(sys_readlinkat,sys_readlinkat,compat_sys_readlinkat)
+SYSCALL(sys_fchmodat,sys_fchmodat,compat_sys_fchmodat)
+SYSCALL(sys_faccessat,sys_faccessat,compat_sys_faccessat)       /* 300 */
+SYSCALL(sys_pselect6,sys_pselect6,compat_sys_pselect6)
+SYSCALL(sys_ppoll,sys_ppoll,compat_sys_ppoll)
+SYSCALL(sys_unshare,sys_unshare,compat_sys_unshare)
 SYSCALL(sys_set_robust_list,sys_set_robust_list,compat_sys_set_robust_list)
 SYSCALL(sys_get_robust_list,sys_get_robust_list,compat_sys_get_robust_list)
-SYSCALL(sys_splice,sys_splice,sys_splice_wrapper)
-SYSCALL(sys_sync_file_range,sys_sync_file_range,sys_sync_file_range_wrapper)
-SYSCALL(sys_tee,sys_tee,sys_tee_wrapper)
+SYSCALL(sys_splice,sys_splice,compat_sys_splice)
+SYSCALL(sys_sync_file_range,sys_sync_file_range,compat_sys_s390_sync_file_range)
+SYSCALL(sys_tee,sys_tee,compat_sys_tee)
 SYSCALL(sys_vmsplice,sys_vmsplice,compat_sys_vmsplice)
 NI_SYSCALL                                                      /* 310 sys_move_pages */
-SYSCALL(sys_getcpu,sys_getcpu,sys_getcpu_wrapper)
+SYSCALL(sys_getcpu,sys_getcpu,compat_sys_getcpu)
 SYSCALL(sys_epoll_pwait,sys_epoll_pwait,compat_sys_epoll_pwait)
-SYSCALL(sys_utimes,sys_utimes,compat_sys_utimes_wrapper)
-SYSCALL(sys_s390_fallocate,sys_fallocate,sys_fallocate_wrapper)
-SYSCALL(sys_utimensat,sys_utimensat,compat_sys_utimensat_wrapper)       /* 315 */
+SYSCALL(sys_utimes,sys_utimes,compat_sys_utimes)
+SYSCALL(sys_s390_fallocate,sys_fallocate,compat_sys_s390_fallocate)
+SYSCALL(sys_utimensat,sys_utimensat,compat_sys_utimensat)       /* 315 */
 SYSCALL(sys_signalfd,sys_signalfd,compat_sys_signalfd)
 NI_SYSCALL                                              /* 317 old sys_timer_fd */
-SYSCALL(sys_eventfd,sys_eventfd,sys_eventfd_wrapper)
-SYSCALL(sys_timerfd_create,sys_timerfd_create,sys_timerfd_create_wrapper)
+SYSCALL(sys_eventfd,sys_eventfd,compat_sys_eventfd)
+SYSCALL(sys_timerfd_create,sys_timerfd_create,compat_sys_timerfd_create)
 SYSCALL(sys_timerfd_settime,sys_timerfd_settime,compat_sys_timerfd_settime) /* 320 */
 SYSCALL(sys_timerfd_gettime,sys_timerfd_gettime,compat_sys_timerfd_gettime)
 SYSCALL(sys_signalfd4,sys_signalfd4,compat_sys_signalfd4)
-SYSCALL(sys_eventfd2,sys_eventfd2,sys_eventfd2_wrapper)
-SYSCALL(sys_inotify_init1,sys_inotify_init1,sys_inotify_init1_wrapper)
-SYSCALL(sys_pipe2,sys_pipe2,sys_pipe2_wrapper) /* 325 */
-SYSCALL(sys_dup3,sys_dup3,sys_dup3_wrapper)
-SYSCALL(sys_epoll_create1,sys_epoll_create1,sys_epoll_create1_wrapper)
+SYSCALL(sys_eventfd2,sys_eventfd2,compat_sys_eventfd2)
+SYSCALL(sys_inotify_init1,sys_inotify_init1,compat_sys_inotify_init1)
+SYSCALL(sys_pipe2,sys_pipe2,compat_sys_pipe2) /* 325 */
+SYSCALL(sys_dup3,sys_dup3,compat_sys_dup3)
+SYSCALL(sys_epoll_create1,sys_epoll_create1,compat_sys_epoll_create1)
 SYSCALL(sys_preadv,sys_preadv,compat_sys_preadv)
 SYSCALL(sys_pwritev,sys_pwritev,compat_sys_pwritev)
 SYSCALL(sys_rt_tgsigqueueinfo,sys_rt_tgsigqueueinfo,compat_sys_rt_tgsigqueueinfo) /* 330 */
-SYSCALL(sys_perf_event_open,sys_perf_event_open,sys_perf_event_open_wrapper)
-SYSCALL(sys_fanotify_init,sys_fanotify_init,sys_fanotify_init_wrapper)
+SYSCALL(sys_perf_event_open,sys_perf_event_open,compat_sys_perf_event_open)
+SYSCALL(sys_fanotify_init,sys_fanotify_init,compat_sys_fanotify_init)
 SYSCALL(sys_fanotify_mark,sys_fanotify_mark,compat_sys_fanotify_mark)
-SYSCALL(sys_prlimit64,sys_prlimit64,sys_prlimit64_wrapper)
-SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,sys_name_to_handle_at_wrapper) /* 335 */
+SYSCALL(sys_prlimit64,sys_prlimit64,compat_sys_prlimit64)
+SYSCALL(sys_name_to_handle_at,sys_name_to_handle_at,compat_sys_name_to_handle_at) /* 335 */
 SYSCALL(sys_open_by_handle_at,sys_open_by_handle_at,compat_sys_open_by_handle_at)
-SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime_wrapper)
-SYSCALL(sys_syncfs,sys_syncfs,sys_syncfs_wrapper)
-SYSCALL(sys_setns,sys_setns,sys_setns_wrapper)
-SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv_wrapper) /* 340 */
-SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev_wrapper)
-SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,sys_s390_runtime_instr_wrapper)
-SYSCALL(sys_kcmp,sys_kcmp,sys_kcmp_wrapper)
-SYSCALL(sys_finit_module,sys_finit_module,sys_finit_module_wrapper)
-SYSCALL(sys_sched_setattr,sys_sched_setattr,sys_sched_setattr_wrapper) /* 345 */
-SYSCALL(sys_sched_getattr,sys_sched_getattr,sys_sched_getattr_wrapper)
+SYSCALL(sys_clock_adjtime,sys_clock_adjtime,compat_sys_clock_adjtime)
+SYSCALL(sys_syncfs,sys_syncfs,compat_sys_syncfs)
+SYSCALL(sys_setns,sys_setns,compat_sys_setns)
+SYSCALL(sys_process_vm_readv,sys_process_vm_readv,compat_sys_process_vm_readv) /* 340 */
+SYSCALL(sys_process_vm_writev,sys_process_vm_writev,compat_sys_process_vm_writev)
+SYSCALL(sys_ni_syscall,sys_s390_runtime_instr,compat_sys_s390_runtime_instr)
+SYSCALL(sys_kcmp,sys_kcmp,compat_sys_kcmp)
+SYSCALL(sys_finit_module,sys_finit_module,compat_sys_finit_module)
+SYSCALL(sys_sched_setattr,sys_sched_setattr,compat_sys_sched_setattr) /* 345 */
+SYSCALL(sys_sched_getattr,sys_sched_getattr,compat_sys_sched_getattr)
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 4b2e3e317004..6298fed11ced 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -451,7 +451,6 @@ static int __init topology_init(void)
         }
         set_topology_timer();
 out:
-        update_cpu_masks();
         return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching);
 }
 device_initcall(topology_init);
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 8216c0e0b2e2..6f9cfa500372 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -13,6 +13,7 @@
 
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
+#include <asm/pgalloc.h>
 #include <asm/virtio-ccw.h>
 #include "kvm-s390.h"
 #include "trace.h"
@@ -86,9 +87,11 @@ static int __diag_ipl_functions(struct kvm_vcpu *vcpu)
         switch (subcode) {
         case 3:
                 vcpu->run->s390_reset_flags = KVM_S390_RESET_CLEAR;
+                page_table_reset_pgste(current->mm, 0, TASK_SIZE);
                 break;
         case 4:
                 vcpu->run->s390_reset_flags = 0;
+                page_table_reset_pgste(current->mm, 0, TASK_SIZE);
                 break;
         default:
                 return -EOPNOTSUPP;
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index e0676f390d57..10b5db3c9bc4 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -68,6 +68,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
         { "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
         { "instruction_stsch", VCPU_STAT(instruction_stsch) },
         { "instruction_chsc", VCPU_STAT(instruction_chsc) },
+        { "instruction_essa", VCPU_STAT(instruction_essa) },
         { "instruction_stsi", VCPU_STAT(instruction_stsi) },
         { "instruction_stfl", VCPU_STAT(instruction_stfl) },
         { "instruction_tprot", VCPU_STAT(instruction_tprot) },
@@ -283,7 +284,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
         if (kvm_is_ucontrol(vcpu->kvm))
                 gmap_free(vcpu->arch.gmap);
 
+        if (vcpu->arch.sie_block->cbrlo)
+                __free_page(__pfn_to_page(
+                                vcpu->arch.sie_block->cbrlo >> PAGE_SHIFT));
         free_page((unsigned long)(vcpu->arch.sie_block));
+
         kvm_vcpu_uninit(vcpu);
         kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
@@ -390,6 +395,8 @@ int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
 {
+        struct page *cbrl;
+
         atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH |
                                                     CPUSTAT_SM |
                                                     CPUSTAT_STOPPED |
@@ -401,6 +408,14 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
         vcpu->arch.sie_block->ecb2  = 8;
         vcpu->arch.sie_block->eca   = 0xC1002001U;
         vcpu->arch.sie_block->fac   = (int) (long) vfacilities;
+        if (kvm_enabled_cmma()) {
+                cbrl = alloc_page(GFP_KERNEL | __GFP_ZERO);
+                if (cbrl) {
+                        vcpu->arch.sie_block->ecb2 |= 0x80;
+                        vcpu->arch.sie_block->ecb2 &= ~0x08;
+                        vcpu->arch.sie_block->cbrlo = page_to_phys(cbrl);
+                }
+        }
         hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
         tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
                      (unsigned long) vcpu);
@@ -761,6 +776,16 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
         return rc;
 }
 
+bool kvm_enabled_cmma(void)
+{
+        if (!MACHINE_IS_LPAR)
+                return false;
+        /* only enable for z10 and later */
+        if (!MACHINE_HAS_EDAT1)
+                return false;
+        return true;
+}
+
 static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
         int rc, exit_reason;
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index f9559b0bd620..564514f410f4 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -156,6 +156,8 @@ void s390_vcpu_block(struct kvm_vcpu *vcpu);
 void s390_vcpu_unblock(struct kvm_vcpu *vcpu);
 void exit_sie(struct kvm_vcpu *vcpu);
 void exit_sie_sync(struct kvm_vcpu *vcpu);
+/* are we going to support cmma? */
+bool kvm_enabled_cmma(void);
 /* implemented in diag.c */
 int kvm_s390_handle_diag(struct kvm_vcpu *vcpu);
 
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index 75beea632a10..aacb6b129914 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -636,8 +636,49 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
         return 0;
 }
 
+static int handle_essa(struct kvm_vcpu *vcpu)
+{
+        /* entries expected to be 1FF */
+        int entries = (vcpu->arch.sie_block->cbrlo & ~PAGE_MASK) >> 3;
+        unsigned long *cbrlo, cbrle;
+        struct gmap *gmap;
+        int i;
+
+        VCPU_EVENT(vcpu, 5, "cmma release %d pages", entries);
+        gmap = vcpu->arch.gmap;
+        vcpu->stat.instruction_essa++;
+        if (!kvm_enabled_cmma() || !vcpu->arch.sie_block->cbrlo)
+                return kvm_s390_inject_program_int(vcpu, PGM_OPERATION);
+
+        if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
+                return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
+
+        if (((vcpu->arch.sie_block->ipb & 0xf0000000) >> 28) > 6)
+                return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+
+        /* Rewind PSW to repeat the ESSA instruction */
+        vcpu->arch.sie_block->gpsw.addr =
+                __rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+        vcpu->arch.sie_block->cbrlo &= PAGE_MASK;       /* reset nceo */
+        cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
+        down_read(&gmap->mm->mmap_sem);
+        for (i = 0; i < entries; ++i) {
+                cbrle = cbrlo[i];
+                if (unlikely(cbrle & ~PAGE_MASK || cbrle < 2 * PAGE_SIZE))
+                        /* invalid entry */
+                        break;
+                /* try to free backing */
+                __gmap_zap(cbrle, gmap);
+        }
+        up_read(&gmap->mm->mmap_sem);
+        if (i < entries)
+                return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
+        return 0;
+}
+
 static const intercept_handler_t b9_handlers[256] = {
         [0x8d] = handle_epsw,
+        [0xab] = handle_essa,
         [0xaf] = handle_pfmf,
 };
 
diff --git a/arch/s390/lib/Makefile b/arch/s390/lib/Makefile
index b068729e50ac..e3fffe1dff51 100644
--- a/arch/s390/lib/Makefile
+++ b/arch/s390/lib/Makefile
@@ -2,8 +2,7 @@
 # Makefile for s390-specific library files..
 #
 
-lib-y += delay.o string.o uaccess_pt.o find.o
+lib-y += delay.o string.o uaccess_pt.o uaccess_mvcos.o find.o
 obj-$(CONFIG_32BIT) += div64.o qrnnd.o ucmpdi2.o mem32.o
 obj-$(CONFIG_64BIT) += mem64.o
-lib-$(CONFIG_64BIT) += uaccess_mvcos.o
 lib-$(CONFIG_SMP) += spinlock.o
diff --git a/arch/s390/lib/find.c b/arch/s390/lib/find.c
index 620d34d6487e..922003c1b90d 100644
--- a/arch/s390/lib/find.c
+++ b/arch/s390/lib/find.c
@@ -4,7 +4,7 @@
  * On s390x the bits are numbered:
  *   |0..............63|64............127|128...........191|192...........255|
  * and on s390:
- *   |0.....31|31....63|64....95|96...127|128..159|160..191|192..223|224..255|
+ *   |0.....31|32....63|64....95|96...127|128..159|160..191|192..223|224..255|
  *
  * The reason for this bit numbering is the fact that the hardware sets bits
  * in a bitmap starting at bit 0 (MSB) and we don't want to scan the bitmap
diff --git a/arch/s390/lib/uaccess.h b/arch/s390/lib/uaccess.h
index b1a22173d027..c7e0e81f4b4e 100644
--- a/arch/s390/lib/uaccess.h
+++ b/arch/s390/lib/uaccess.h
@@ -6,7 +6,11 @@
 #ifndef __ARCH_S390_LIB_UACCESS_H
 #define __ARCH_S390_LIB_UACCESS_H
 
-extern int futex_atomic_op_pt(int, u32 __user *, int, int *);
-extern int futex_atomic_cmpxchg_pt(u32 *, u32 __user *, u32, u32);
+unsigned long copy_from_user_pt(void *to, const void __user *from, unsigned long n);
+unsigned long copy_to_user_pt(void __user *to, const void *from, unsigned long n);
+unsigned long copy_in_user_pt(void __user *to, const void __user *from, unsigned long n);
+unsigned long clear_user_pt(void __user *to, unsigned long n);
+unsigned long strnlen_user_pt(const char __user *src, unsigned long count);
+long strncpy_from_user_pt(char *dst, const char __user *src, long count);
 
 #endif /* __ARCH_S390_LIB_UACCESS_H */
diff --git a/arch/s390/lib/uaccess_mvcos.c b/arch/s390/lib/uaccess_mvcos.c
index 4b7993bf69b9..ae97b8df11aa 100644
--- a/arch/s390/lib/uaccess_mvcos.c
+++ b/arch/s390/lib/uaccess_mvcos.c
@@ -6,8 +6,11 @@
  *               Gerald Schaefer (gerald.schaefer@de.ibm.com)
  */
 
+#include <linux/jump_label.h>
 #include <linux/errno.h>
+#include <linux/init.h>
 #include <linux/mm.h>
+#include <asm/facility.h>
 #include <asm/uaccess.h>
 #include <asm/futex.h>
 #include "uaccess.h"
@@ -26,7 +29,10 @@
 #define SLR     "slgr"
 #endif
 
-static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x)
+static struct static_key have_mvcos = STATIC_KEY_INIT_TRUE;
+
+static inline unsigned long copy_from_user_mvcos(void *x, const void __user *ptr,
+                                                 unsigned long size)
 {
         register unsigned long reg0 asm("0") = 0x81UL;
         unsigned long tmp1, tmp2;
@@ -65,7 +71,16 @@ static size_t copy_from_user_mvcos(size_t size, const void __user *ptr, void *x)
         return size;
 }
 
-static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x)
+unsigned long __copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+        if (static_key_true(&have_mvcos))
+                return copy_from_user_mvcos(to, from, n);
+        return copy_from_user_pt(to, from, n);
+}
+EXPORT_SYMBOL(__copy_from_user);
+
+static inline unsigned long copy_to_user_mvcos(void __user *ptr, const void *x,
+                                               unsigned long size)
 {
         register unsigned long reg0 asm("0") = 0x810000UL;
         unsigned long tmp1, tmp2;
@@ -94,8 +109,16 @@ static size_t copy_to_user_mvcos(size_t size, void __user *ptr, const void *x)
         return size;
 }
 
-static size_t copy_in_user_mvcos(size_t size, void __user *to,
-                                 const void __user *from)
+unsigned long __copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+        if (static_key_true(&have_mvcos))
+                return copy_to_user_mvcos(to, from, n);
+        return copy_to_user_pt(to, from, n);
+}
+EXPORT_SYMBOL(__copy_to_user);
+
+static inline unsigned long copy_in_user_mvcos(void __user *to, const void __user *from,
+                                               unsigned long size)
 {
         register unsigned long reg0 asm("0") = 0x810081UL;
         unsigned long tmp1, tmp2;
@@ -117,7 +140,15 @@ static size_t copy_in_user_mvcos(size_t size, void __user *to,
         return size;
 }
 
-static size_t clear_user_mvcos(size_t size, void __user *to)
+unsigned long __copy_in_user(void __user *to, const void __user *from, unsigned long n)
+{
+        if (static_key_true(&have_mvcos))
+                return copy_in_user_mvcos(to, from, n);
+        return copy_in_user_pt(to, from, n);
+}
+EXPORT_SYMBOL(__copy_in_user);
+
+static inline unsigned long clear_user_mvcos(void __user *to, unsigned long size)
 {
         register unsigned long reg0 asm("0") = 0x810000UL;
         unsigned long tmp1, tmp2;
@@ -145,17 +176,26 @@ static size_t clear_user_mvcos(size_t size, void __user *to)
         return size;
 }
 
-static size_t strnlen_user_mvcos(size_t count, const char __user *src)
+unsigned long __clear_user(void __user *to, unsigned long size)
 {
-        size_t done, len, offset, len_str;
+        if (static_key_true(&have_mvcos))
+                return clear_user_mvcos(to, size);
+        return clear_user_pt(to, size);
+}
+EXPORT_SYMBOL(__clear_user);
+
+static inline unsigned long strnlen_user_mvcos(const char __user *src,
+                                               unsigned long count)
+{
+        unsigned long done, len, offset, len_str;
         char buf[256];
 
         done = 0;
         do {
-                offset = (size_t)src & ~PAGE_MASK;
+                offset = (unsigned long)src & ~PAGE_MASK;
                 len = min(256UL, PAGE_SIZE - offset);
                 len = min(count - done, len);
-                if (copy_from_user_mvcos(len, src, buf))
+                if (copy_from_user_mvcos(buf, src, len))
                         return 0;
                 len_str = strnlen(buf, len);
                 done += len_str;
@@ -164,18 +204,26 @@ static size_t strnlen_user_mvcos(size_t count, const char __user *src)
         return done + 1;
 }
 
-static size_t strncpy_from_user_mvcos(size_t count, const char __user *src,
-                                      char *dst)
+unsigned long __strnlen_user(const char __user *src, unsigned long count)
 {
-        size_t done, len, offset, len_str;
+        if (static_key_true(&have_mvcos))
+                return strnlen_user_mvcos(src, count);
+        return strnlen_user_pt(src, count);
+}
+EXPORT_SYMBOL(__strnlen_user);
 
-        if (unlikely(!count))
+static inline long strncpy_from_user_mvcos(char *dst, const char __user *src,
+                                           long count)
+{
+        unsigned long done, len, offset, len_str;
+
+        if (unlikely(count <= 0))
                 return 0;
         done = 0;
         do {
-                offset = (size_t)src & ~PAGE_MASK;
+                offset = (unsigned long)src & ~PAGE_MASK;
                 len = min(count - done, PAGE_SIZE - offset);
-                if (copy_from_user_mvcos(len, src, dst))
+                if (copy_from_user_mvcos(dst, src, len))
                         return -EFAULT;
                 len_str = strnlen(dst, len);
                 done += len_str;
@@ -185,13 +233,31 @@ static size_t strncpy_from_user_mvcos(size_t count, const char __user *src,
         return done;
 }
 
-struct uaccess_ops uaccess_mvcos = {
-        .copy_from_user = copy_from_user_mvcos,
-        .copy_to_user = copy_to_user_mvcos,
-        .copy_in_user = copy_in_user_mvcos,
-        .clear_user = clear_user_mvcos,
-        .strnlen_user = strnlen_user_mvcos,
-        .strncpy_from_user = strncpy_from_user_mvcos,
-        .futex_atomic_op = futex_atomic_op_pt,
-        .futex_atomic_cmpxchg = futex_atomic_cmpxchg_pt,
-};
+long __strncpy_from_user(char *dst, const char __user *src, long count)
+{
+        if (static_key_true(&have_mvcos))
+                return strncpy_from_user_mvcos(dst, src, count);
+        return strncpy_from_user_pt(dst, src, count);
+}
+EXPORT_SYMBOL(__strncpy_from_user);
+
+/*
+ * The uaccess page tabe walk variant can be enforced with the "uaccesspt"
+ * kernel parameter. This is mainly for debugging purposes.
+ */
+static int force_uaccess_pt __initdata;
+
+static int __init parse_uaccess_pt(char *__unused)
+{
+        force_uaccess_pt = 1;
+        return 0;
+}
+early_param("uaccesspt", parse_uaccess_pt);
+
+static int __init uaccess_init(void)
+{
+        if (IS_ENABLED(CONFIG_32BIT) || force_uaccess_pt || !test_facility(27))
+                static_key_slow_dec(&have_mvcos);
+        return 0;
+}
+early_initcall(uaccess_init);
diff --git a/arch/s390/lib/uaccess_pt.c b/arch/s390/lib/uaccess_pt.c
index 61ebcc9ccb34..8d39760bae68 100644
--- a/arch/s390/lib/uaccess_pt.c
+++ b/arch/s390/lib/uaccess_pt.c
@@ -22,7 +22,7 @@
 #define SLR     "slgr"
 #endif
 
-static size_t strnlen_kernel(size_t count, const char __user *src)
+static unsigned long strnlen_kernel(const char __user *src, unsigned long count)
 {
         register unsigned long reg0 asm("0") = 0UL;
         unsigned long tmp1, tmp2;
@@ -42,8 +42,8 @@ static size_t strnlen_kernel(size_t count, const char __user *src)
         return count;
 }
 
-static size_t copy_in_kernel(size_t count, void __user *to,
-                             const void __user *from)
+static unsigned long copy_in_kernel(void __user *to, const void __user *from,
+                                    unsigned long count)
 {
         unsigned long tmp1;
 
@@ -146,8 +146,8 @@ static unsigned long follow_table(struct mm_struct *mm,
 
 #endif /* CONFIG_64BIT */
 
-static __always_inline size_t __user_copy_pt(unsigned long uaddr, void *kptr,
-                                             size_t n, int write_user)
+static inline unsigned long __user_copy_pt(unsigned long uaddr, void *kptr,
+                                           unsigned long n, int write_user)
 {
         struct mm_struct *mm = current->mm;
         unsigned long offset, done, size, kaddr;
@@ -189,8 +189,7 @@ fault:
  * Do DAT for user address by page table walk, return kernel address.
  * This function needs to be called with current->mm->page_table_lock held.
  */
-static __always_inline unsigned long __dat_user_addr(unsigned long uaddr,
-                                                     int write)
+static inline unsigned long __dat_user_addr(unsigned long uaddr, int write)
 {
         struct mm_struct *mm = current->mm;
         unsigned long kaddr;
@@ -211,29 +210,29 @@ fault:
         return 0;
 }
 
-static size_t copy_from_user_pt(size_t n, const void __user *from, void *to)
+unsigned long copy_from_user_pt(void *to, const void __user *from, unsigned long n)
 {
-        size_t rc;
+        unsigned long rc;
 
         if (segment_eq(get_fs(), KERNEL_DS))
-                return copy_in_kernel(n, (void __user *) to, from);
+                return copy_in_kernel((void __user *) to, from, n);
         rc = __user_copy_pt((unsigned long) from, to, n, 0);
         if (unlikely(rc))
                 memset(to + n - rc, 0, rc);
         return rc;
 }
 
-static size_t copy_to_user_pt(size_t n, void __user *to, const void *from)
+unsigned long copy_to_user_pt(void __user *to, const void *from, unsigned long n)
 {
         if (segment_eq(get_fs(), KERNEL_DS))
-                return copy_in_kernel(n, to, (void __user *) from);
+                return copy_in_kernel(to, (void __user *) from, n);
         return __user_copy_pt((unsigned long) to, (void *) from, n, 1);
 }
 
-static size_t clear_user_pt(size_t n, void __user *to)
+unsigned long clear_user_pt(void __user *to, unsigned long n)
 {
         void *zpage = (void *) empty_zero_page;
-        long done, size, ret;
+        unsigned long done, size, ret;
 
         done = 0;
         do {
@@ -242,7 +241,7 @@ static size_t clear_user_pt(size_t n, void __user *to)
                 else
                         size = n - done;
                 if (segment_eq(get_fs(), KERNEL_DS))
-                        ret = copy_in_kernel(n, to, (void __user *) zpage);
+                        ret = copy_in_kernel(to, (void __user *) zpage, n);
                 else
                         ret = __user_copy_pt((unsigned long) to, zpage, size, 1);
                 done += size;
@@ -253,17 +252,17 @@ static size_t clear_user_pt(size_t n, void __user *to)
         return 0;
 }
 
-static size_t strnlen_user_pt(size_t count, const char __user *src)
+unsigned long strnlen_user_pt(const char __user *src, unsigned long count)
 {
         unsigned long uaddr = (unsigned long) src;
         struct mm_struct *mm = current->mm;
         unsigned long offset, done, len, kaddr;
-        size_t len_str;
+        unsigned long len_str;
 
         if (unlikely(!count))
                 return 0;
         if (segment_eq(get_fs(), KERNEL_DS))
-                return strnlen_kernel(count, src);
+                return strnlen_kernel(src, count);
         if (!mm)
                 return 0;
         done = 0;
@@ -289,19 +288,18 @@ fault:
         goto retry;
 }
 
-static size_t strncpy_from_user_pt(size_t count, const char __user *src,
-                                   char *dst)
+long strncpy_from_user_pt(char *dst, const char __user *src, long count)
 {
-        size_t done, len, offset, len_str;
+        unsigned long done, len, offset, len_str;
 
-        if (unlikely(!count))
+        if (unlikely(count <= 0))
                 return 0;
         done = 0;
         do {
-                offset = (size_t)src & ~PAGE_MASK;
+                offset = (unsigned long)src & ~PAGE_MASK;
                 len = min(count - done, PAGE_SIZE - offset);
                 if (segment_eq(get_fs(), KERNEL_DS)) {
-                        if (copy_in_kernel(len, (void __user *) dst, src))
+                        if (copy_in_kernel((void __user *) dst, src, len))
                                 return -EFAULT;
                 } else {
                         if (__user_copy_pt((unsigned long) src, dst, len, 0))
@@ -315,8 +313,8 @@ static size_t strncpy_from_user_pt(size_t count, const char __user *src,
         return done;
 }
 
-static size_t copy_in_user_pt(size_t n, void __user *to,
-                              const void __user *from)
+unsigned long copy_in_user_pt(void __user *to, const void __user *from,
+                              unsigned long n)
 {
         struct mm_struct *mm = current->mm;
         unsigned long offset_max, uaddr, done, size, error_code;
@@ -326,7 +324,7 @@ static size_t copy_in_user_pt(size_t n, void __user *to,
         int write_user;
 
         if (segment_eq(get_fs(), KERNEL_DS))
-                return copy_in_kernel(n, to, from);
+                return copy_in_kernel(to, from, n);
         if (!mm)
                 return n;
         done = 0;
@@ -411,7 +409,7 @@ static int __futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
         return ret;
 }
 
-int futex_atomic_op_pt(int op, u32 __user *uaddr, int oparg, int *old)
+int __futex_atomic_op_inuser(int op, u32 __user *uaddr, int oparg, int *old)
 {
         int ret;
 
@@ -449,8 +447,8 @@ static int __futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
         return ret;
 }
 
-int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
-                            u32 oldval, u32 newval)
+int futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
+                                  u32 oldval, u32 newval)
 {
         int ret;
 
@@ -471,14 +469,3 @@ int futex_atomic_cmpxchg_pt(u32 *uval, u32 __user *uaddr,
         put_page(virt_to_page(uaddr));
         return ret;
 }
-
-struct uaccess_ops uaccess_pt = {
-        .copy_from_user         = copy_from_user_pt,
-        .copy_to_user           = copy_to_user_pt,
-        .copy_in_user           = copy_in_user_pt,
-        .clear_user             = clear_user_pt,
-        .strnlen_user           = strnlen_user_pt,
-        .strncpy_from_user      = strncpy_from_user_pt,
-        .futex_atomic_op        = futex_atomic_op_pt,
-        .futex_atomic_cmpxchg   = futex_atomic_cmpxchg_pt,
-};
diff --git a/arch/s390/mm/maccess.c b/arch/s390/mm/maccess.c
index d1e0e0c7a7e2..2a2e35416d2f 100644
--- a/arch/s390/mm/maccess.c
+++ b/arch/s390/mm/maccess.c
@@ -128,7 +128,7 @@ void memcpy_absolute(void *dest, void *src, size_t count)
 /*
  * Copy memory from kernel (real) to user (virtual)
  */
-int copy_to_user_real(void __user *dest, void *src, size_t count)
+int copy_to_user_real(void __user *dest, void *src, unsigned long count)
 {
         int offs = 0, size, rc;
         char *buf;
@@ -152,32 +152,6 @@ out:
 }
 
 /*
- * Copy memory from user (virtual) to kernel (real)
- */
-int copy_from_user_real(void *dest, void __user *src, size_t count)
-{
-        int offs = 0, size, rc;
-        char *buf;
-
-        buf = (char *) __get_free_page(GFP_KERNEL);
-        if (!buf)
-                return -ENOMEM;
-        rc = -EFAULT;
-        while (offs < count) {
-                size = min(PAGE_SIZE, count - offs);
-                if (copy_from_user(buf, src + offs, size))
-                        goto out;
-                if (memcpy_real(dest + offs, buf, size))
-                        goto out;
-                offs += size;
-        }
-        rc = 0;
-out:
-        free_page((unsigned long) buf);
-        return rc;
-}
-
-/*
  * Check if physical address is within prefix or zero page
  */
 static int is_swapped(unsigned long addr)
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 3584ed9b20a1..796c9320c709 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -17,6 +17,7 @@
 #include <linux/quicklist.h>
 #include <linux/rcupdate.h>
 #include <linux/slab.h>
+#include <linux/swapops.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -594,6 +595,82 @@ unsigned long gmap_fault(unsigned long address, struct gmap *gmap)
 }
 EXPORT_SYMBOL_GPL(gmap_fault);
 
+static void gmap_zap_swap_entry(swp_entry_t entry, struct mm_struct *mm)
+{
+        if (!non_swap_entry(entry))
+                dec_mm_counter(mm, MM_SWAPENTS);
+        else if (is_migration_entry(entry)) {
+                struct page *page = migration_entry_to_page(entry);
+
+                if (PageAnon(page))
+                        dec_mm_counter(mm, MM_ANONPAGES);
+                else
+                        dec_mm_counter(mm, MM_FILEPAGES);
+        }
+        free_swap_and_cache(entry);
+}
+
+/**
+ * The mm->mmap_sem lock must be held
+ */
+static void gmap_zap_unused(struct mm_struct *mm, unsigned long address)
+{
+        unsigned long ptev, pgstev;
+        spinlock_t *ptl;
+        pgste_t pgste;
+        pte_t *ptep, pte;
+
+        ptep = get_locked_pte(mm, address, &ptl);
+        if (unlikely(!ptep))
+                return;
+        pte = *ptep;
+        if (!pte_swap(pte))
+                goto out_pte;
+        /* Zap unused and logically-zero pages */
+        pgste = pgste_get_lock(ptep);
+        pgstev = pgste_val(pgste);
+        ptev = pte_val(pte);
+        if (((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) ||
+            ((pgstev & _PGSTE_GPS_ZERO) && (ptev & _PAGE_INVALID))) {
+                gmap_zap_swap_entry(pte_to_swp_entry(pte), mm);
+                pte_clear(mm, address, ptep);
+        }
+        pgste_set_unlock(ptep, pgste);
+out_pte:
+        pte_unmap_unlock(*ptep, ptl);
+}
+
+/*
+ * this function is assumed to be called with mmap_sem held
+ */
+void __gmap_zap(unsigned long address, struct gmap *gmap)
+{
+        unsigned long *table, *segment_ptr;
+        unsigned long segment, pgstev, ptev;
+        struct gmap_pgtable *mp;
+        struct page *page;
+
+        segment_ptr = gmap_table_walk(address, gmap);
+        if (IS_ERR(segment_ptr))
+                return;
+        segment = *segment_ptr;
+        if (segment & _SEGMENT_ENTRY_INVALID)
+                return;
+        page = pfn_to_page(segment >> PAGE_SHIFT);
+        mp = (struct gmap_pgtable *) page->index;
+        address = mp->vmaddr | (address & ~PMD_MASK);
+        /* Page table is present */
+        table = (unsigned long *)(segment & _SEGMENT_ENTRY_ORIGIN);
+        table = table + ((address >> 12) & 0xff);
+        pgstev = table[PTRS_PER_PTE];
+        ptev = table[0];
+        /* quick check, checked again with locks held */
+        if (((pgstev & _PGSTE_GPS_USAGE_MASK) == _PGSTE_GPS_USAGE_UNUSED) ||
+            ((pgstev & _PGSTE_GPS_ZERO) && (ptev & _PAGE_INVALID)))
+                gmap_zap_unused(gmap->mm, address);
+}
+EXPORT_SYMBOL_GPL(__gmap_zap);
+
 void gmap_discard(unsigned long from, unsigned long to, struct gmap *gmap)
 {
 
@@ -671,7 +748,7 @@ EXPORT_SYMBOL_GPL(gmap_unregister_ipte_notifier);
 /**
  * gmap_ipte_notify - mark a range of ptes for invalidation notification
  * @gmap: pointer to guest mapping meta data structure
- * @address: virtual address in the guest address space
+ * @start: virtual address in the guest address space
  * @len: size of area
  *
  * Returns 0 if for each page in the given range a gmap mapping exists and
@@ -725,13 +802,12 @@ EXPORT_SYMBOL_GPL(gmap_ipte_notify);
 /**
  * gmap_do_ipte_notify - call all invalidation callbacks for a specific pte.
  * @mm: pointer to the process mm_struct
- * @addr: virtual address in the process address space
  * @pte: pointer to the page table entry
  *
  * This function is assumed to be called with the page table lock held
  * for the pte to notify.
  */
-void gmap_do_ipte_notify(struct mm_struct *mm, unsigned long addr, pte_t *pte)
+void gmap_do_ipte_notify(struct mm_struct *mm, pte_t *pte)
 {
         unsigned long segment_offset;
         struct gmap_notifier *nb;
@@ -802,6 +878,78 @@ static inline void page_table_free_pgste(unsigned long *table)
         __free_page(page);
 }
 
+static inline unsigned long page_table_reset_pte(struct mm_struct *mm,
+                        pmd_t *pmd, unsigned long addr, unsigned long end)
+{
+        pte_t *start_pte, *pte;
+        spinlock_t *ptl;
+        pgste_t pgste;
+
+        start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+        pte = start_pte;
+        do {
+                pgste = pgste_get_lock(pte);
+                pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+                pgste_set_unlock(pte, pgste);
+        } while (pte++, addr += PAGE_SIZE, addr != end);
+        pte_unmap_unlock(start_pte, ptl);
+
+        return addr;
+}
+
+static inline unsigned long page_table_reset_pmd(struct mm_struct *mm,
+                        pud_t *pud, unsigned long addr, unsigned long end)
+{
+        unsigned long next;
+        pmd_t *pmd;
+
+        pmd = pmd_offset(pud, addr);
+        do {
+                next = pmd_addr_end(addr, end);
+                if (pmd_none_or_clear_bad(pmd))
+                        continue;
+                next = page_table_reset_pte(mm, pmd, addr, next);
+        } while (pmd++, addr = next, addr != end);
+
+        return addr;
+}
+
+static inline unsigned long page_table_reset_pud(struct mm_struct *mm,
+                        pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+        unsigned long next;
+        pud_t *pud;
+
+        pud = pud_offset(pgd, addr);
+        do {
+                next = pud_addr_end(addr, end);
+                if (pud_none_or_clear_bad(pud))
+                        continue;
+                next = page_table_reset_pmd(mm, pud, addr, next);
+        } while (pud++, addr = next, addr != end);
+
+        return addr;
+}
+
+void page_table_reset_pgste(struct mm_struct *mm,
+                        unsigned long start, unsigned long end)
+{
+        unsigned long addr, next;
+        pgd_t *pgd;
+
+        addr = start;
+        down_read(&mm->mmap_sem);
+        pgd = pgd_offset(mm, addr);
+        do {
+                next = pgd_addr_end(addr, end);
+                if (pgd_none_or_clear_bad(pgd))
+                        continue;
+                next = page_table_reset_pud(mm, pgd, addr, next);
+        } while (pgd++, addr = next, addr != end);
+        up_read(&mm->mmap_sem);
+}
+EXPORT_SYMBOL(page_table_reset_pgste);
+
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
                           unsigned long key, bool nq)
 {
@@ -1248,7 +1396,7 @@ void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
 {
         struct list_head *lh = (struct list_head *) pgtable;
 
-        assert_spin_locked(&mm->page_table_lock);
+        assert_spin_locked(pmd_lockptr(mm, pmdp));
 
         /* FIFO */
         if (!pmd_huge_pte(mm, pmdp))
@@ -1264,7 +1412,7 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
         pgtable_t pgtable;
         pte_t *ptep;
 
-        assert_spin_locked(&mm->page_table_lock);
+        assert_spin_locked(pmd_lockptr(mm, pmdp));
 
         /* FIFO */
         pgtable = pmd_huge_pte(mm, pmdp);
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 75c69b402e05..c5c66840ac00 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -139,7 +139,7 @@ void zpci_debug_exit_device(struct zpci_dev *zdev)
 int __init zpci_debug_init(void)
 {
         /* event trace buffer */
-        pci_debug_msg_id = debug_register("pci_msg", 16, 1, 16 * sizeof(long));
+        pci_debug_msg_id = debug_register("pci_msg", 8, 1, 8 * sizeof(long));
         if (!pci_debug_msg_id)
                 return -EINVAL;
         debug_register_view(pci_debug_msg_id, &debug_sprintf_view);
diff --git a/arch/s390/pci/pci_dma.c b/arch/s390/pci/pci_dma.c
index 60c11a629d96..f91c03119804 100644
--- a/arch/s390/pci/pci_dma.c
+++ b/arch/s390/pci/pci_dma.c
@@ -206,11 +206,13 @@ static void dma_cleanup_tables(struct zpci_dev *zdev)
         zdev->dma_table = NULL;
 }
 
-static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev, unsigned long start,
-                                   int size)
+static unsigned long __dma_alloc_iommu(struct zpci_dev *zdev,
+                                       unsigned long start, int size)
 {
-        unsigned long boundary_size = 0x1000000;
+        unsigned long boundary_size;
 
+        boundary_size = ALIGN(dma_get_seg_boundary(&zdev->pdev->dev) + 1,
+                              PAGE_SIZE) >> PAGE_SHIFT;
         return iommu_area_alloc(zdev->iommu_bitmap, zdev->iommu_pages,
                                 start, size, 0, boundary_size, 0);
 }
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 146b9d5e89f8..2f947aba4bd4 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -1,10 +1,12 @@
 
 header-y +=
 
+
 generic-y += barrier.h
 generic-y += clkdev.h
+generic-y += cputime.h
 generic-y += hash.h
+generic-y += mcs_spinlock.h
+generic-y += preempt.h
 generic-y += trace_clock.h
 generic-y += xor.h
-generic-y += preempt.h
-
diff --git a/arch/score/include/asm/cputime.h b/arch/score/include/asm/cputime.h
deleted file mode 100644
index 1fced99f0d67..000000000000
--- a/arch/score/include/asm/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SCORE_CPUTIME_H
-#define _ASM_SCORE_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* _ASM_SCORE_CPUTIME_H */
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 6357710753d5..364d204298fa 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -123,15 +123,6 @@ config SYS_SUPPORTS_NUMA
 config SYS_SUPPORTS_PCI
         bool
 
-config SYS_SUPPORTS_CMT
-        bool
-
-config SYS_SUPPORTS_MTU2
-        bool
-
-config SYS_SUPPORTS_TMU
-        bool
-
 config STACKTRACE_SUPPORT
         def_bool y
 
@@ -191,14 +182,14 @@ config CPU_SH3
         bool
         select CPU_HAS_INTEVT
         select CPU_HAS_SR_RB
-        select SYS_SUPPORTS_TMU
+        select SYS_SUPPORTS_SH_TMU
 
 config CPU_SH4
         bool
         select CPU_HAS_INTEVT
         select CPU_HAS_SR_RB
         select CPU_HAS_FPU if !CPU_SH4AL_DSP
-        select SYS_SUPPORTS_TMU
+        select SYS_SUPPORTS_SH_TMU
         select SYS_SUPPORTS_HUGETLBFS if MMU
 
 config CPU_SH4A
@@ -213,7 +204,7 @@ config CPU_SH4AL_DSP
 config CPU_SH5
         bool
         select CPU_HAS_FPU
-        select SYS_SUPPORTS_TMU
+        select SYS_SUPPORTS_SH_TMU
         select SYS_SUPPORTS_HUGETLBFS if MMU
 
 config CPU_SHX2
@@ -250,7 +241,7 @@ choice
 config CPU_SUBTYPE_SH7619
         bool "Support SH7619 processor"
         select CPU_SH2
-        select SYS_SUPPORTS_CMT
+        select SYS_SUPPORTS_SH_CMT
 
 # SH-2A Processor Support
 
@@ -258,50 +249,50 @@ config CPU_SUBTYPE_SH7201
         bool "Support SH7201 processor"
         select CPU_SH2A
         select CPU_HAS_FPU
-        select SYS_SUPPORTS_MTU2
+        select SYS_SUPPORTS_SH_MTU2
  
 config CPU_SUBTYPE_SH7203
         bool "Support SH7203 processor"
         select CPU_SH2A
         select CPU_HAS_FPU
-        select SYS_SUPPORTS_CMT
-        select SYS_SUPPORTS_MTU2
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_MTU2
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select PINCTRL
 
 config CPU_SUBTYPE_SH7206
         bool "Support SH7206 processor"
         select CPU_SH2A
-        select SYS_SUPPORTS_CMT
-        select SYS_SUPPORTS_MTU2
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_MTU2
 
 config CPU_SUBTYPE_SH7263
         bool "Support SH7263 processor"
         select CPU_SH2A
         select CPU_HAS_FPU
-        select SYS_SUPPORTS_CMT
-        select SYS_SUPPORTS_MTU2
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_MTU2
 
 config CPU_SUBTYPE_SH7264
         bool "Support SH7264 processor"
         select CPU_SH2A
         select CPU_HAS_FPU
-        select SYS_SUPPORTS_CMT
-        select SYS_SUPPORTS_MTU2
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_MTU2
         select PINCTRL
 
 config CPU_SUBTYPE_SH7269
         bool "Support SH7269 processor"
         select CPU_SH2A
         select CPU_HAS_FPU
-        select SYS_SUPPORTS_CMT
-        select SYS_SUPPORTS_MTU2
+        select SYS_SUPPORTS_SH_CMT
+        select SYS_SUPPORTS_SH_MTU2
         select PINCTRL
 
 config CPU_SUBTYPE_MXG
         bool "Support MX-G processor"
         select CPU_SH2A
-        select SYS_SUPPORTS_MTU2
+        select SYS_SUPPORTS_SH_MTU2
         help
           Select MX-G if running on an R8A03022BG part.
 
@@ -354,7 +345,7 @@ config CPU_SUBTYPE_SH7720
         bool "Support SH7720 processor"
         select CPU_SH3
         select CPU_HAS_DSP
-        select SYS_SUPPORTS_CMT
+        select SYS_SUPPORTS_SH_CMT
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select USB_ARCH_HAS_OHCI
         select USB_OHCI_SH if USB_OHCI_HCD
@@ -366,7 +357,7 @@ config CPU_SUBTYPE_SH7721
         bool "Support SH7721 processor"
         select CPU_SH3
         select CPU_HAS_DSP
-        select SYS_SUPPORTS_CMT
+        select SYS_SUPPORTS_SH_CMT
         select USB_ARCH_HAS_OHCI
         select USB_OHCI_SH if USB_OHCI_HCD
         help
@@ -422,7 +413,7 @@ config CPU_SUBTYPE_SH7723
         select CPU_SHX2
         select ARCH_SHMOBILE
         select ARCH_SPARSEMEM_ENABLE
-        select SYS_SUPPORTS_CMT
+        select SYS_SUPPORTS_SH_CMT
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select PINCTRL
         help
@@ -434,7 +425,7 @@ config CPU_SUBTYPE_SH7724
         select CPU_SHX2
         select ARCH_SHMOBILE
         select ARCH_SPARSEMEM_ENABLE
-        select SYS_SUPPORTS_CMT
+        select SYS_SUPPORTS_SH_CMT
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select PINCTRL
         help
@@ -514,7 +505,7 @@ config CPU_SUBTYPE_SH7343
         bool "Support SH7343 processor"
         select CPU_SH4AL_DSP
         select ARCH_SHMOBILE
-        select SYS_SUPPORTS_CMT
+        select SYS_SUPPORTS_SH_CMT
 
 config CPU_SUBTYPE_SH7722
         bool "Support SH7722 processor"
@@ -523,7 +514,7 @@ config CPU_SUBTYPE_SH7722
         select ARCH_SHMOBILE
         select ARCH_SPARSEMEM_ENABLE
         select SYS_SUPPORTS_NUMA
-        select SYS_SUPPORTS_CMT
+        select SYS_SUPPORTS_SH_CMT
         select ARCH_WANT_OPTIONAL_GPIOLIB
         select PINCTRL
 
@@ -534,7 +525,7 @@ config CPU_SUBTYPE_SH7366
         select ARCH_SHMOBILE
         select ARCH_SPARSEMEM_ENABLE
         select SYS_SUPPORTS_NUMA
-        select SYS_SUPPORTS_CMT
+        select SYS_SUPPORTS_SH_CMT
 
 endchoice
 
@@ -567,27 +558,6 @@ source "arch/sh/boards/Kconfig"
 
 menu "Timer and clock configuration"
 
-config SH_TIMER_TMU
-        bool "TMU timer driver"
-        depends on SYS_SUPPORTS_TMU
-        default y
-        help
-          This enables the build of the TMU timer driver.
-
-config SH_TIMER_CMT
-        bool "CMT timer driver"
-        depends on SYS_SUPPORTS_CMT
-        default y
-        help
-          This enables build of the CMT timer driver.
-
-config SH_TIMER_MTU2
-        bool "MTU2 timer driver"
-        depends on SYS_SUPPORTS_MTU2
-        default y
-        help
-          This enables build of the MTU2 timer driver.
-
 config SH_PCLK_FREQ
         int "Peripheral clock frequency (in Hz)"
         depends on SH_CLK_CPG_LEGACY
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 0cd7198a4524..c19e47dacb31 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -8,18 +8,21 @@ generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
 generic-y += fcntl.h
+generic-y += hash.h
 generic-y += ioctl.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += local64.h
+generic-y += mcs_spinlock.h
+generic-y += mman.h
+generic-y += msgbuf.h
 generic-y += param.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += poll.h
-generic-y += mman.h
-generic-y += msgbuf.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sembuf.h
@@ -34,5 +37,3 @@ generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += ucontext.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/sh/include/cpu-sh2/cpu/cache.h b/arch/sh/include/cpu-sh2/cpu/cache.h
index 673515bc4135..aa1b2b9088a7 100644
--- a/arch/sh/include/cpu-sh2/cpu/cache.h
+++ b/arch/sh/include/cpu-sh2/cpu/cache.h
@@ -18,7 +18,7 @@
 #define SH_CACHE_ASSOC          8
 
 #if defined(CONFIG_CPU_SUBTYPE_SH7619)
-#define CCR             0xffffffec
+#define SH_CCR          0xffffffec
 
 #define CCR_CACHE_CE    0x01    /* Cache enable */
 #define CCR_CACHE_WT    0x02    /* CCR[bit1=1,bit2=1] */
diff --git a/arch/sh/include/cpu-sh2a/cpu/cache.h b/arch/sh/include/cpu-sh2a/cpu/cache.h
index defb0baa5a06..b27ce92cb600 100644
--- a/arch/sh/include/cpu-sh2a/cpu/cache.h
+++ b/arch/sh/include/cpu-sh2a/cpu/cache.h
@@ -17,8 +17,8 @@
 #define SH_CACHE_COMBINED       4
 #define SH_CACHE_ASSOC          8
 
-#define CCR             0xfffc1000 /* CCR1 */
-#define CCR2            0xfffc1004
+#define SH_CCR          0xfffc1000 /* CCR1 */
+#define SH_CCR2         0xfffc1004
 
 /*
  * Most of the SH-2A CCR1 definitions resemble the SH-4 ones. All others not
diff --git a/arch/sh/include/cpu-sh3/cpu/cache.h b/arch/sh/include/cpu-sh3/cpu/cache.h
index bee2d81c56bf..29700fd88c75 100644
--- a/arch/sh/include/cpu-sh3/cpu/cache.h
+++ b/arch/sh/include/cpu-sh3/cpu/cache.h
@@ -17,7 +17,7 @@
 #define SH_CACHE_COMBINED       4
 #define SH_CACHE_ASSOC          8
 
-#define CCR             0xffffffec      /* Address of Cache Control Register */
+#define SH_CCR          0xffffffec      /* Address of Cache Control Register */
 
 #define CCR_CACHE_CE    0x01    /* Cache Enable */
 #define CCR_CACHE_WT    0x02    /* Write-Through (for P0,U0,P3) (else writeback) */
diff --git a/arch/sh/include/cpu-sh4/cpu/cache.h b/arch/sh/include/cpu-sh4/cpu/cache.h
index 7bfb9e8b069c..92c4cd119b66 100644
--- a/arch/sh/include/cpu-sh4/cpu/cache.h
+++ b/arch/sh/include/cpu-sh4/cpu/cache.h
@@ -17,7 +17,7 @@
 #define SH_CACHE_COMBINED       4
 #define SH_CACHE_ASSOC          8
 
-#define CCR             0xff00001c      /* Address of Cache Control Register */
+#define SH_CCR          0xff00001c      /* Address of Cache Control Register */
 #define CCR_CACHE_OCE   0x0001  /* Operand Cache Enable */
 #define CCR_CACHE_WT    0x0002  /* Write-Through (for P0,U0,P3) (else writeback)*/
 #define CCR_CACHE_CB    0x0004  /* Copy-Back (for P1) (else writethrough) */
diff --git a/arch/sh/kernel/cpu/init.c b/arch/sh/kernel/cpu/init.c
index ecf83cd158dc..0d7360d549c1 100644
--- a/arch/sh/kernel/cpu/init.c
+++ b/arch/sh/kernel/cpu/init.c
@@ -112,7 +112,7 @@ static void cache_init(void)
         unsigned long ccr, flags;
 
         jump_to_uncached();
-        ccr = __raw_readl(CCR);
+        ccr = __raw_readl(SH_CCR);
 
         /*
          * At this point we don't know whether the cache is enabled or not - a
@@ -189,7 +189,7 @@ static void cache_init(void)
 
         l2_cache_init();
 
-        __raw_writel(flags, CCR);
+        __raw_writel(flags, SH_CCR);
         back_to_cached();
 }
 #else
diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 2ea4483fd722..be616ee0cf87 100644
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -16,7 +16,6 @@
 #include <linux/thread_info.h>
 #include <linux/irqflags.h>
 #include <linux/smp.h>
-#include <linux/cpuidle.h>
 #include <linux/atomic.h>
 #include <asm/pgalloc.h>
 #include <asm/smp.h>
@@ -40,8 +39,7 @@ void arch_cpu_idle_dead(void)
 
 void arch_cpu_idle(void)
 {
-        if (cpuidle_idle_call())
-                sh_idle();
+        sh_idle();
 }
 
 void __init select_idle_routine(void)
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 0833736afa32..65a1ecd77f96 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -217,19 +217,6 @@ void __init init_IRQ(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void route_irq(struct irq_data *data, unsigned int irq, unsigned int cpu)
-{
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_chip *chip = irq_data_get_irq_chip(data);
-
-        printk(KERN_INFO "IRQ%u: moving from cpu%u to cpu%u\n",
-               irq, data->node, cpu);
-
-        raw_spin_lock_irq(&desc->lock);
-        chip->irq_set_affinity(data, cpumask_of(cpu), false);
-        raw_spin_unlock_irq(&desc->lock);
-}
-
 /*
  * The CPU has been marked offline.  Migrate IRQs off this CPU.  If
  * the affinity settings do not allow other CPUs, force them onto any
@@ -250,11 +237,8 @@ void migrate_irqs(void)
                                                     irq, cpu);
 
                                 cpumask_setall(data->affinity);
-                                newcpu = cpumask_any_and(data->affinity,
-                                                         cpu_online_mask);
                         }
-
-                        route_irq(data, irq, newcpu);
+                        irq_set_affinity(irq, data->affinity);
                 }
         }
 }
diff --git a/arch/sh/mm/cache-debugfs.c b/arch/sh/mm/cache-debugfs.c
index 115725198038..777e50f33c00 100644
--- a/arch/sh/mm/cache-debugfs.c
+++ b/arch/sh/mm/cache-debugfs.c
@@ -36,7 +36,7 @@ static int cache_seq_show(struct seq_file *file, void *iter)
          */
         jump_to_uncached();
 
-        ccr = __raw_readl(CCR);
+        ccr = __raw_readl(SH_CCR);
         if ((ccr & CCR_CACHE_ENABLE) == 0) {
                 back_to_cached();
 
diff --git a/arch/sh/mm/cache-sh2.c b/arch/sh/mm/cache-sh2.c
index defcf719f2e8..a74259f2f981 100644
--- a/arch/sh/mm/cache-sh2.c
+++ b/arch/sh/mm/cache-sh2.c
@@ -63,9 +63,9 @@ static void sh2__flush_invalidate_region(void *start, int size)
         local_irq_save(flags);
         jump_to_uncached();
 
-        ccr = __raw_readl(CCR);
+        ccr = __raw_readl(SH_CCR);
         ccr |= CCR_CACHE_INVALIDATE;
-        __raw_writel(ccr, CCR);
+        __raw_writel(ccr, SH_CCR);
 
         back_to_cached();
         local_irq_restore(flags);
diff --git a/arch/sh/mm/cache-sh2a.c b/arch/sh/mm/cache-sh2a.c
index 949e2d3138a0..ee87d081259b 100644
--- a/arch/sh/mm/cache-sh2a.c
+++ b/arch/sh/mm/cache-sh2a.c
@@ -134,7 +134,8 @@ static void sh2a__flush_invalidate_region(void *start, int size)
 
         /* If there are too many pages then just blow the cache */
         if (((end - begin) >> PAGE_SHIFT) >= MAX_OCACHE_PAGES) {
-                __raw_writel(__raw_readl(CCR) | CCR_OCACHE_INVALIDATE, CCR);
+                __raw_writel(__raw_readl(SH_CCR) | CCR_OCACHE_INVALIDATE,
+                             SH_CCR);
         } else {
                 for (v = begin; v < end; v += L1_CACHE_BYTES)
                         sh2a_invalidate_line(CACHE_OC_ADDRESS_ARRAY, v);
@@ -167,7 +168,8 @@ static void sh2a_flush_icache_range(void *args)
         /* I-Cache invalidate */
         /* If there are too many pages then just blow the cache */
         if (((end - start) >> PAGE_SHIFT) >= MAX_ICACHE_PAGES) {
-                __raw_writel(__raw_readl(CCR) | CCR_ICACHE_INVALIDATE, CCR);
+                __raw_writel(__raw_readl(SH_CCR) | CCR_ICACHE_INVALIDATE,
+                             SH_CCR);
         } else {
                 for (v = start; v < end; v += L1_CACHE_BYTES)
                         sh2a_invalidate_line(CACHE_IC_ADDRESS_ARRAY, v);
diff --git a/arch/sh/mm/cache-sh4.c b/arch/sh/mm/cache-sh4.c
index 0e529285b28d..51d8f7f31d1d 100644
--- a/arch/sh/mm/cache-sh4.c
+++ b/arch/sh/mm/cache-sh4.c
@@ -133,9 +133,9 @@ static void flush_icache_all(void)
         jump_to_uncached();
 
         /* Flush I-cache */
-        ccr = __raw_readl(CCR);
+        ccr = __raw_readl(SH_CCR);
         ccr |= CCR_CACHE_ICI;
-        __raw_writel(ccr, CCR);
+        __raw_writel(ccr, SH_CCR);
 
         /*
          * back_to_cached() will take care of the barrier for us, don't add
diff --git a/arch/sh/mm/cache-shx3.c b/arch/sh/mm/cache-shx3.c
index c0adbee97b5f..24c58b7dc022 100644
--- a/arch/sh/mm/cache-shx3.c
+++ b/arch/sh/mm/cache-shx3.c
@@ -19,7 +19,7 @@ void __init shx3_cache_init(void)
 {
         unsigned int ccr;
 
-        ccr = __raw_readl(CCR);
+        ccr = __raw_readl(SH_CCR);
 
         /*
          * If we've got cache aliases, resolve them in hardware.
@@ -40,5 +40,5 @@ void __init shx3_cache_init(void)
         ccr |= CCR_CACHE_IBE;
 #endif
 
-        writel_uncached(ccr, CCR);
+        writel_uncached(ccr, SH_CCR);
 }
diff --git a/arch/sh/mm/cache.c b/arch/sh/mm/cache.c
index 616966a96cba..097c2cdd117f 100644
--- a/arch/sh/mm/cache.c
+++ b/arch/sh/mm/cache.c
@@ -285,8 +285,8 @@ void __init cpu_cache_init(void)
 {
         unsigned int cache_disabled = 0;
 
-#ifdef CCR
-        cache_disabled = !(__raw_readl(CCR) & CCR_CACHE_ENABLE);
+#ifdef SH_CCR
+        cache_disabled = !(__raw_readl(SH_CCR) & CCR_CACHE_ENABLE);
 #endif
 
         compute_alias(&boot_cpu_data.icache);
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 4b60a0c325ec..a45821818003 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -6,15 +6,16 @@ generic-y += cputime.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h
-generic-y += linkage.h
-generic-y += local64.h
-generic-y += mutex.h
+generic-y += hash.h
 generic-y += irq_regs.h
+generic-y += linkage.h
 generic-y += local.h
+generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += module.h
+generic-y += mutex.h
+generic-y += preempt.h
 generic-y += serial.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += word-at-a-time.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/sparc/include/asm/smp_64.h b/arch/sparc/include/asm/smp_64.h
index dd3bef4b9896..05710393959f 100644
--- a/arch/sparc/include/asm/smp_64.h
+++ b/arch/sparc/include/asm/smp_64.h
@@ -32,7 +32,6 @@
 
 DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
 extern cpumask_t cpu_core_map[NR_CPUS];
-extern int sparc64_multi_core;
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
diff --git a/arch/sparc/include/asm/topology_64.h b/arch/sparc/include/asm/topology_64.h
index 1754390a426f..a2d10fc64faf 100644
--- a/arch/sparc/include/asm/topology_64.h
+++ b/arch/sparc/include/asm/topology_64.h
@@ -42,8 +42,6 @@ static inline int pcibus_to_node(struct pci_bus *pbus)
 #define topology_core_id(cpu)                   (cpu_data(cpu).core_id)
 #define topology_core_cpumask(cpu)              (&cpu_core_map[cpu])
 #define topology_thread_cpumask(cpu)            (&per_cpu(cpu_sibling_map, cpu))
-#define mc_capable()                            (sparc64_multi_core)
-#define smt_capable()                           (sparc64_multi_core)
 #endif /* CONFIG_SMP */
 
 extern cpumask_t cpu_core_map[NR_CPUS];
diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c
index b90bf23e3aab..a1a4400d4025 100644
--- a/arch/sparc/kernel/mdesc.c
+++ b/arch/sparc/kernel/mdesc.c
@@ -896,10 +896,6 @@ void mdesc_fill_in_cpu_data(cpumask_t *mask)
 
         mdesc_iterate_over_cpus(fill_in_one_cpu, NULL, mask);
 
-#ifdef CONFIG_SMP
-        sparc64_multi_core = 1;
-#endif
-
         hp = mdesc_grab();
 
         set_core_ids(hp);
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 32a280ec38c1..d7b4967f8fa6 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -58,9 +58,12 @@ void arch_cpu_idle(void)
 {
         if (tlb_type != hypervisor) {
                 touch_nmi_watchdog();
+                local_irq_enable();
         } else {
                 unsigned long pstate;
 
+                local_irq_enable();
+
                 /* The sun4v sleeping code requires that we have PSTATE.IE cleared over
                  * the cpu sleep hypervisor call.
                  */
@@ -82,7 +85,6 @@ void arch_cpu_idle(void)
                         : "=&r" (pstate)
                         : "i" (PSTATE_IE));
         }
-        local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c
index 6b39125eb927..9a690d39c01b 100644
--- a/arch/sparc/kernel/prom_64.c
+++ b/arch/sparc/kernel/prom_64.c
@@ -555,9 +555,6 @@ static void *fill_in_one_cpu(struct device_node *dp, int cpuid, int arg)
 
                 cpu_data(cpuid).core_id = portid + 1;
                 cpu_data(cpuid).proc_id = portid;
-#ifdef CONFIG_SMP
-                sparc64_multi_core = 1;
-#endif
         } else {
                 cpu_data(cpuid).dcache_size =
                         of_getintprop_default(dp, "dcache-size", 16 * 1024);
diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c
index b085311dcd0e..9781048161ab 100644
--- a/arch/sparc/kernel/smp_64.c
+++ b/arch/sparc/kernel/smp_64.c
@@ -53,8 +53,6 @@
 
 #include "cpumap.h"
 
-int sparc64_multi_core __read_mostly;
-
 DEFINE_PER_CPU(cpumask_t, cpu_sibling_map) = CPU_MASK_NONE;
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly =
         { [0 ... NR_CPUS-1] = CPU_MASK_NONE };
diff --git a/arch/sparc/kernel/syscalls.S b/arch/sparc/kernel/syscalls.S
index 87729fff13b9..33a17e7b3ccd 100644
--- a/arch/sparc/kernel/syscalls.S
+++ b/arch/sparc/kernel/syscalls.S
@@ -189,7 +189,8 @@ linux_sparc_syscall32:
          mov    %i0, %l5                                ! IEU1
 5:      call    %l7                                     ! CTI   Group brk forced
          srl    %i5, 0, %o5                             ! IEU1
-        ba,a,pt %xcc, 3f
+        ba,pt   %xcc, 3f
+         sra    %o0, 0, %o0
 
         /* Linux native system calls enter here... */
         .align  32
@@ -217,7 +218,6 @@ linux_sparc_syscall:
 3:      stx     %o0, [%sp + PTREGS_OFF + PT_V9_I0]
 ret_sys_call:
         ldx     [%sp + PTREGS_OFF + PT_V9_TSTATE], %g3
-        sra     %o0, 0, %o0
         mov     %ulo(TSTATE_XCARRY | TSTATE_ICARRY), %g2
         sllx    %g2, 32, %g2
 
diff --git a/arch/sparc/kernel/time_64.c b/arch/sparc/kernel/time_64.c
index c3d82b5f54ca..24e8b8705e7f 100644
--- a/arch/sparc/kernel/time_64.c
+++ b/arch/sparc/kernel/time_64.c
@@ -733,7 +733,7 @@ void __irq_entry timer_interrupt(int irq, struct pt_regs *regs)
         irq_enter();
 
         local_cpu_data().irq0_irqs++;
-        kstat_incr_irqs_this_cpu(0, irq_to_desc(0));
+        kstat_incr_irq_this_cpu(0);
 
         if (unlikely(!evt->event_handler)) {
                 printk(KERN_WARNING
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 3b3a360b429a..f5d506fdddad 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -273,7 +273,7 @@ void __init pgtable_cache_init(void)
                 prom_halt();
         }
 
-        for (i = 0; i < 8; i++) {
+        for (i = 0; i < ARRAY_SIZE(tsb_cache_names); i++) {
                 unsigned long size = 8192 << i;
                 const char *name = tsb_cache_names[i];
 
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index 3793c75e45d9..0aa5675e7025 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -11,6 +11,7 @@ generic-y += errno.h
 generic-y += exec.h
 generic-y += fb.h
 generic-y += fcntl.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
@@ -18,12 +19,14 @@ generic-y += ipcbuf.h
 generic-y += irq_regs.h
 generic-y += local.h
 generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += param.h
 generic-y += parport.h
 generic-y += poll.h
 generic-y += posix_types.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sembuf.h
@@ -38,5 +41,3 @@ generic-y += termios.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 88a330dcdede..a5e4b6068213 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -1,8 +1,28 @@
-generic-y += bug.h cputime.h device.h emergency-restart.h futex.h hardirq.h
-generic-y += hw_irq.h irq_regs.h kdebug.h percpu.h sections.h topology.h xor.h
-generic-y += ftrace.h pci.h io.h param.h delay.h mutex.h current.h exec.h
-generic-y += switch_to.h clkdev.h
-generic-y += trace_clock.h
-generic-y += preempt.h
-generic-y += hash.h
 generic-y += barrier.h
+generic-y += bug.h
+generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += current.h
+generic-y += delay.h
+generic-y += device.h
+generic-y += emergency-restart.h
+generic-y += exec.h
+generic-y += ftrace.h
+generic-y += futex.h
+generic-y += hardirq.h
+generic-y += hash.h
+generic-y += hw_irq.h
+generic-y += io.h
+generic-y += irq_regs.h
+generic-y += kdebug.h
+generic-y += mcs_spinlock.h
+generic-y += mutex.h
+generic-y += param.h
+generic-y += pci.h
+generic-y += percpu.h
+generic-y += preempt.h
+generic-y += sections.h
+generic-y += switch_to.h
+generic-y += topology.h
+generic-y += trace_clock.h
+generic-y += xor.h
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index 3ef4f9d9bf5d..1e5fb872a4aa 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += fcntl.h
 generic-y += ftrace.h
 generic-y += futex.h
 generic-y += hardirq.h
+generic-y += hash.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
@@ -24,6 +25,7 @@ generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
 generic-y += local.h
+generic-y += mcs_spinlock.h
 generic-y += mman.h
 generic-y += module.h
 generic-y += msgbuf.h
@@ -32,6 +34,7 @@ generic-y += parport.h
 generic-y += percpu.h
 generic-y += poll.h
 generic-y += posix_types.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
@@ -60,5 +63,3 @@ generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0af5250d914f..8453fe1342ea 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1585,6 +1585,20 @@ config EFI_STUB
 
           See Documentation/efi-stub.txt for more information.
 
+config EFI_MIXED
+        bool "EFI mixed-mode support"
+        depends on EFI_STUB && X86_64
+        ---help---
+           Enabling this feature allows a 64-bit kernel to be booted
+           on a 32-bit firmware, provided that your CPU supports 64-bit
+           mode.
+
+           Note that it is not possible to boot a mixed-mode enabled
+           kernel via the EFI boot stub - a bootloader that supports
+           the EFI handover protocol must be used.
+
+           If unsure, say N.
+
 config SECCOMP
         def_bool y
         prompt "Enable seccomp to safely compute untrusted bytecode"
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index c026cca5602c..f3aaf231b4e5 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -341,10 +341,6 @@ config X86_USE_3DNOW
         def_bool y
         depends on (MCYRIXIII || MK7 || MGEODE_LX) && !UML
 
-config X86_OOSTORE
-        def_bool y
-        depends on (MWINCHIP3D || MWINCHIPC6) && MTRR
-
 #
 # P6_NOPs are a relatively minor optimization that require a family >=
 # 6 processor, except that it is broken on certain VIA chips.
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 321a52ccf63a..61bd2ad94281 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -81,6 +81,15 @@ config X86_PTDUMP
           kernel.
           If in doubt, say "N"
 
+config EFI_PGT_DUMP
+        bool "Dump the EFI pagetable"
+        depends on EFI && X86_PTDUMP
+        ---help---
+          Enable this if you want to dump the EFI page table before
+          enabling virtual mode. This can be used to debug miscellaneous
+          issues with the mapping of the EFI runtime regions into that
+          table.
+
 config DEBUG_RODATA
         bool "Write protect kernel read-only data structures"
         default y
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index eeda43abed6e..3b9348a0c1a4 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -82,8 +82,8 @@ else
         KBUILD_AFLAGS += -m64
         KBUILD_CFLAGS += -m64
 
-        # Don't autogenerate MMX or SSE instructions
-        KBUILD_CFLAGS += -mno-mmx -mno-sse
+        # Don't autogenerate traditional x87, MMX or SSE instructions
+        KBUILD_CFLAGS += -mno-mmx -mno-sse -mno-80387 -mno-fp-ret-in-387
 
         # Use -mpreferred-stack-boundary=3 if supported.
         KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
@@ -152,6 +152,7 @@ cfi-sections := $(call as-instr,.cfi_sections .debug_frame,-DCONFIG_AS_CFI_SECTI
 
 # does binutils support specific instructions?
 asinstr := $(call as-instr,fxsaveq (%rax),-DCONFIG_AS_FXSAVEQ=1)
+asinstr += $(call as-instr,crc32l %eax$(comma)%eax,-DCONFIG_AS_CRC32=1)
 avx_instr := $(call as-instr,vxorps %ymm0$(comma)%ymm1$(comma)%ymm2,-DCONFIG_AS_AVX=1)
 avx2_instr :=$(call as-instr,vpbroadcastb %xmm0$(comma)%ymm1,-DCONFIG_AS_AVX2=1)
 
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 878df7e88cd4..abb9eba61b50 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -80,7 +80,7 @@ targets += voffset.h
 $(obj)/voffset.h: vmlinux FORCE
         $(call if_changed,voffset)
 
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi_pe_entry\|efi_stub_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) . \(startup_32\|startup_64\|efi32_stub_entry\|efi64_stub_entry\|efi_pe_entry\|input_data\|_end\|z_.*\)$$/\#define ZO_\2 0x\1/p'
 
 quiet_cmd_zoffset = ZOFFSET $@
       cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index 90a21f430117..4dbf967da50d 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -111,7 +111,7 @@ struct mem_vector {
 };
 
 #define MEM_AVOID_MAX 5
-struct mem_vector mem_avoid[MEM_AVOID_MAX];
+static struct mem_vector mem_avoid[MEM_AVOID_MAX];
 
 static bool mem_contains(struct mem_vector *region, struct mem_vector *item)
 {
@@ -180,7 +180,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 }
 
 /* Does this memory vector overlap a known avoided area? */
-bool mem_avoid_overlap(struct mem_vector *img)
+static bool mem_avoid_overlap(struct mem_vector *img)
 {
         int i;
 
@@ -192,8 +192,9 @@ bool mem_avoid_overlap(struct mem_vector *img)
         return false;
 }
 
-unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET / CONFIG_PHYSICAL_ALIGN];
-unsigned long slot_max = 0;
+static unsigned long slots[CONFIG_RANDOMIZE_BASE_MAX_OFFSET /
+                           CONFIG_PHYSICAL_ALIGN];
+static unsigned long slot_max;
 
 static void slots_append(unsigned long addr)
 {
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index a7677babf946..1e6146137f8e 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -19,10 +19,272 @@
 
 static efi_system_table_t *sys_table;
 
+static struct efi_config *efi_early;
+
+#define efi_call_early(f, ...)                                          \
+        efi_early->call(efi_early->f, __VA_ARGS__);
+
+#define BOOT_SERVICES(bits)                                             \
+static void setup_boot_services##bits(struct efi_config *c)             \
+{                                                                       \
+        efi_system_table_##bits##_t *table;                             \
+        efi_boot_services_##bits##_t *bt;                               \
+                                                                        \
+        table = (typeof(table))sys_table;                               \
+                                                                        \
+        c->text_output = table->con_out;                                \
+                                                                        \
+        bt = (typeof(bt))(unsigned long)(table->boottime);              \
+                                                                        \
+        c->allocate_pool = bt->allocate_pool;                           \
+        c->allocate_pages = bt->allocate_pages;                         \
+        c->get_memory_map = bt->get_memory_map;                         \
+        c->free_pool = bt->free_pool;                                   \
+        c->free_pages = bt->free_pages;                                 \
+        c->locate_handle = bt->locate_handle;                           \
+        c->handle_protocol = bt->handle_protocol;                       \
+        c->exit_boot_services = bt->exit_boot_services;                 \
+}
+BOOT_SERVICES(32);
+BOOT_SERVICES(64);
 
-#include "../../../../drivers/firmware/efi/efi-stub-helper.c"
+static void efi_printk(efi_system_table_t *, char *);
+static void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
+
+static efi_status_t
+__file_size32(void *__fh, efi_char16_t *filename_16,
+              void **handle, u64 *file_sz)
+{
+        efi_file_handle_32_t *h, *fh = __fh;
+        efi_file_info_t *info;
+        efi_status_t status;
+        efi_guid_t info_guid = EFI_FILE_INFO_ID;
+        u32 info_sz;
+
+        status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
+                                 EFI_FILE_MODE_READ, (u64)0);
+        if (status != EFI_SUCCESS) {
+                efi_printk(sys_table, "Failed to open file: ");
+                efi_char16_printk(sys_table, filename_16);
+                efi_printk(sys_table, "\n");
+                return status;
+        }
+
+        *handle = h;
+
+        info_sz = 0;
+        status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+                                 &info_sz, NULL);
+        if (status != EFI_BUFFER_TOO_SMALL) {
+                efi_printk(sys_table, "Failed to get file info size\n");
+                return status;
+        }
+
+grow:
+        status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+                                info_sz, (void **)&info);
+        if (status != EFI_SUCCESS) {
+                efi_printk(sys_table, "Failed to alloc mem for file info\n");
+                return status;
+        }
+
+        status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+                                 &info_sz, info);
+        if (status == EFI_BUFFER_TOO_SMALL) {
+                efi_call_early(free_pool, info);
+                goto grow;
+        }
+
+        *file_sz = info->file_size;
+        efi_call_early(free_pool, info);
+
+        if (status != EFI_SUCCESS)
+                efi_printk(sys_table, "Failed to get initrd info\n");
+
+        return status;
+}
+
+static efi_status_t
+__file_size64(void *__fh, efi_char16_t *filename_16,
+              void **handle, u64 *file_sz)
+{
+        efi_file_handle_64_t *h, *fh = __fh;
+        efi_file_info_t *info;
+        efi_status_t status;
+        efi_guid_t info_guid = EFI_FILE_INFO_ID;
+        u32 info_sz;
 
+        status = efi_early->call((unsigned long)fh->open, fh, &h, filename_16,
+                                 EFI_FILE_MODE_READ, (u64)0);
+        if (status != EFI_SUCCESS) {
+                efi_printk(sys_table, "Failed to open file: ");
+                efi_char16_printk(sys_table, filename_16);
+                efi_printk(sys_table, "\n");
+                return status;
+        }
 
+        *handle = h;
+
+        info_sz = 0;
+        status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+                                 &info_sz, NULL);
+        if (status != EFI_BUFFER_TOO_SMALL) {
+                efi_printk(sys_table, "Failed to get file info size\n");
+                return status;
+        }
+
+grow:
+        status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+                                info_sz, (void **)&info);
+        if (status != EFI_SUCCESS) {
+                efi_printk(sys_table, "Failed to alloc mem for file info\n");
+                return status;
+        }
+
+        status = efi_early->call((unsigned long)h->get_info, h, &info_guid,
+                                 &info_sz, info);
+        if (status == EFI_BUFFER_TOO_SMALL) {
+                efi_call_early(free_pool, info);
+                goto grow;
+        }
+
+        *file_sz = info->file_size;
+        efi_call_early(free_pool, info);
+
+        if (status != EFI_SUCCESS)
+                efi_printk(sys_table, "Failed to get initrd info\n");
+
+        return status;
+}
+static efi_status_t
+efi_file_size(efi_system_table_t *sys_table, void *__fh,
+              efi_char16_t *filename_16, void **handle, u64 *file_sz)
+{
+        if (efi_early->is64)
+                return __file_size64(__fh, filename_16, handle, file_sz);
+
+        return __file_size32(__fh, filename_16, handle, file_sz);
+}
+
+static inline efi_status_t
+efi_file_read(void *__fh, void *handle, unsigned long *size, void *addr)
+{
+        unsigned long func;
+
+        if (efi_early->is64) {
+                efi_file_handle_64_t *fh = __fh;
+
+                func = (unsigned long)fh->read;
+                return efi_early->call(func, handle, size, addr);
+        } else {
+                efi_file_handle_32_t *fh = __fh;
+
+                func = (unsigned long)fh->read;
+                return efi_early->call(func, handle, size, addr);
+        }
+}
+
+static inline efi_status_t efi_file_close(void *__fh, void *handle)
+{
+        if (efi_early->is64) {
+                efi_file_handle_64_t *fh = __fh;
+
+                return efi_early->call((unsigned long)fh->close, handle);
+        } else {
+                efi_file_handle_32_t *fh = __fh;
+
+                return efi_early->call((unsigned long)fh->close, handle);
+        }
+}
+
+static inline efi_status_t __open_volume32(void *__image, void **__fh)
+{
+        efi_file_io_interface_t *io;
+        efi_loaded_image_32_t *image = __image;
+        efi_file_handle_32_t *fh;
+        efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+        efi_status_t status;
+        void *handle = (void *)(unsigned long)image->device_handle;
+        unsigned long func;
+
+        status = efi_call_early(handle_protocol, handle,
+                                &fs_proto, (void **)&io);
+        if (status != EFI_SUCCESS) {
+                efi_printk(sys_table, "Failed to handle fs_proto\n");
+                return status;
+        }
+
+        func = (unsigned long)io->open_volume;
+        status = efi_early->call(func, io, &fh);
+        if (status != EFI_SUCCESS)
+                efi_printk(sys_table, "Failed to open volume\n");
+
+        *__fh = fh;
+        return status;
+}
+
+static inline efi_status_t __open_volume64(void *__image, void **__fh)
+{
+        efi_file_io_interface_t *io;
+        efi_loaded_image_64_t *image = __image;
+        efi_file_handle_64_t *fh;
+        efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+        efi_status_t status;
+        void *handle = (void *)(unsigned long)image->device_handle;
+        unsigned long func;
+
+        status = efi_call_early(handle_protocol, handle,
+                                &fs_proto, (void **)&io);
+        if (status != EFI_SUCCESS) {
+                efi_printk(sys_table, "Failed to handle fs_proto\n");
+                return status;
+        }
+
+        func = (unsigned long)io->open_volume;
+        status = efi_early->call(func, io, &fh);
+        if (status != EFI_SUCCESS)
+                efi_printk(sys_table, "Failed to open volume\n");
+
+        *__fh = fh;
+        return status;
+}
+
+static inline efi_status_t
+efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
+{
+        if (efi_early->is64)
+                return __open_volume64(__image, __fh);
+
+        return __open_volume32(__image, __fh);
+}
+
+static void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
+{
+        unsigned long output_string;
+        size_t offset;
+
+        if (efi_early->is64) {
+                struct efi_simple_text_output_protocol_64 *out;
+                u64 *func;
+
+                offset = offsetof(typeof(*out), output_string);
+                output_string = efi_early->text_output + offset;
+                func = (u64 *)output_string;
+
+                efi_early->call(*func, efi_early->text_output, str);
+        } else {
+                struct efi_simple_text_output_protocol_32 *out;
+                u32 *func;
+
+                offset = offsetof(typeof(*out), output_string);
+                output_string = efi_early->text_output + offset;
+                func = (u32 *)output_string;
+
+                efi_early->call(*func, efi_early->text_output, str);
+        }
+}
+
+#include "../../../../drivers/firmware/efi/efi-stub-helper.c"
 
 static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 {
@@ -47,105 +309,97 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
         *size = len;
 }
 
-static efi_status_t setup_efi_pci(struct boot_params *params)
+static efi_status_t
+__setup_efi_pci32(efi_pci_io_protocol_32 *pci, struct pci_setup_rom **__rom)
 {
-        efi_pci_io_protocol *pci;
+        struct pci_setup_rom *rom = NULL;
         efi_status_t status;
-        void **pci_handle;
-        efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
-        unsigned long nr_pci, size = 0;
-        int i;
-        struct setup_data *data;
+        unsigned long size;
+        uint64_t attributes;
 
-        data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+        status = efi_early->call(pci->attributes, pci,
+                                 EfiPciIoAttributeOperationGet, 0, 0,
+                                 &attributes);
+        if (status != EFI_SUCCESS)
+                return status;
 
-        while (data && data->next)
-                data = (struct setup_data *)(unsigned long)data->next;
+        if (!pci->romimage || !pci->romsize)
+                return EFI_INVALID_PARAMETER;
 
-        status = efi_call_phys5(sys_table->boottime->locate_handle,
-                                EFI_LOCATE_BY_PROTOCOL, &pci_proto,
-                                NULL, &size, pci_handle);
+        size = pci->romsize + sizeof(*rom);
 
-        if (status == EFI_BUFFER_TOO_SMALL) {
-                status = efi_call_phys3(sys_table->boottime->allocate_pool,
-                                        EFI_LOADER_DATA, size, &pci_handle);
+        status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
+        if (status != EFI_SUCCESS)
+                return status;
 
-                if (status != EFI_SUCCESS)
-                        return status;
+        memset(rom, 0, sizeof(*rom));
 
-                status = efi_call_phys5(sys_table->boottime->locate_handle,
-                                        EFI_LOCATE_BY_PROTOCOL, &pci_proto,
-                                        NULL, &size, pci_handle);
-        }
+        rom->data.type = SETUP_PCI;
+        rom->data.len = size - sizeof(struct setup_data);
+        rom->data.next = 0;
+        rom->pcilen = pci->romsize;
+        *__rom = rom;
 
-        if (status != EFI_SUCCESS)
-                goto free_handle;
-
-        nr_pci = size / sizeof(void *);
-        for (i = 0; i < nr_pci; i++) {
-                void *h = pci_handle[i];
-                uint64_t attributes;
-                struct pci_setup_rom *rom;
+        status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+                                 PCI_VENDOR_ID, 1, &(rom->vendor));
 
-                status = efi_call_phys3(sys_table->boottime->handle_protocol,
-                                        h, &pci_proto, &pci);
+        if (status != EFI_SUCCESS)
+                goto free_struct;
 
-                if (status != EFI_SUCCESS)
-                        continue;
+        status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+                                 PCI_DEVICE_ID, 1, &(rom->devid));
 
-                if (!pci)
-                        continue;
+        if (status != EFI_SUCCESS)
+                goto free_struct;
 
-#ifdef CONFIG_X86_64
-                status = efi_call_phys4(pci->attributes, pci,
-                                        EfiPciIoAttributeOperationGet, 0,
-                                        &attributes);
-#else
-                status = efi_call_phys5(pci->attributes, pci,
-                                        EfiPciIoAttributeOperationGet, 0, 0,
-                                        &attributes);
-#endif
-                if (status != EFI_SUCCESS)
-                        continue;
+        status = efi_early->call(pci->get_location, pci, &(rom->segment),
+                                 &(rom->bus), &(rom->device), &(rom->function));
 
-                if (!pci->romimage || !pci->romsize)
-                        continue;
+        if (status != EFI_SUCCESS)
+                goto free_struct;
 
-                size = pci->romsize + sizeof(*rom);
+        memcpy(rom->romdata, pci->romimage, pci->romsize);
+        return status;
 
-                status = efi_call_phys3(sys_table->boottime->allocate_pool,
-                                EFI_LOADER_DATA, size, &rom);
+free_struct:
+        efi_call_early(free_pool, rom);
+        return status;
+}
 
-                if (status != EFI_SUCCESS)
-                        continue;
+static efi_status_t
+setup_efi_pci32(struct boot_params *params, void **pci_handle,
+                unsigned long size)
+{
+        efi_pci_io_protocol_32 *pci = NULL;
+        efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+        u32 *handles = (u32 *)(unsigned long)pci_handle;
+        efi_status_t status;
+        unsigned long nr_pci;
+        struct setup_data *data;
+        int i;
 
-                rom->data.type = SETUP_PCI;
-                rom->data.len = size - sizeof(struct setup_data);
-                rom->data.next = 0;
-                rom->pcilen = pci->romsize;
+        data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
 
-                status = efi_call_phys5(pci->pci.read, pci,
-                                        EfiPciIoWidthUint16, PCI_VENDOR_ID,
-                                        1, &(rom->vendor));
+        while (data && data->next)
+                data = (struct setup_data *)(unsigned long)data->next;
 
-                if (status != EFI_SUCCESS)
-                        goto free_struct;
+        nr_pci = size / sizeof(u32);
+        for (i = 0; i < nr_pci; i++) {
+                struct pci_setup_rom *rom = NULL;
+                u32 h = handles[i];
 
-                status = efi_call_phys5(pci->pci.read, pci,
-                                        EfiPciIoWidthUint16, PCI_DEVICE_ID,
-                                        1, &(rom->devid));
+                status = efi_call_early(handle_protocol, h,
+                                        &pci_proto, (void **)&pci);
 
                 if (status != EFI_SUCCESS)
-                        goto free_struct;
+                        continue;
 
-                status = efi_call_phys5(pci->get_location, pci,
-                                        &(rom->segment), &(rom->bus),
-                                        &(rom->device), &(rom->function));
+                if (!pci)
+                        continue;
 
+                status = __setup_efi_pci32(pci, &rom);
                 if (status != EFI_SUCCESS)
-                        goto free_struct;
-
-                memcpy(rom->romdata, pci->romimage, pci->romsize);
+                        continue;
 
                 if (data)
                         data->next = (unsigned long)rom;
@@ -154,105 +408,155 @@ static efi_status_t setup_efi_pci(struct boot_params *params)
 
                 data = (struct setup_data *)rom;
 
-                continue;
-        free_struct:
-                efi_call_phys1(sys_table->boottime->free_pool, rom);
         }
 
-free_handle:
-        efi_call_phys1(sys_table->boottime->free_pool, pci_handle);
         return status;
 }
 
-/*
- * See if we have Graphics Output Protocol
- */
-static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
-                              unsigned long size)
+static efi_status_t
+__setup_efi_pci64(efi_pci_io_protocol_64 *pci, struct pci_setup_rom **__rom)
 {
-        struct efi_graphics_output_protocol *gop, *first_gop;
-        struct efi_pixel_bitmask pixel_info;
-        unsigned long nr_gops;
+        struct pci_setup_rom *rom;
         efi_status_t status;
-        void **gop_handle;
-        u16 width, height;
-        u32 fb_base, fb_size;
-        u32 pixels_per_scan_line;
-        int pixel_format;
-        int i;
+        unsigned long size;
+        uint64_t attributes;
 
-        status = efi_call_phys3(sys_table->boottime->allocate_pool,
-                                EFI_LOADER_DATA, size, &gop_handle);
+        status = efi_early->call(pci->attributes, pci,
+                                 EfiPciIoAttributeOperationGet, 0,
+                                 &attributes);
         if (status != EFI_SUCCESS)
                 return status;
 
-        status = efi_call_phys5(sys_table->boottime->locate_handle,
-                                EFI_LOCATE_BY_PROTOCOL, proto,
-                                NULL, &size, gop_handle);
+        if (!pci->romimage || !pci->romsize)
+                return EFI_INVALID_PARAMETER;
+
+        size = pci->romsize + sizeof(*rom);
+
+        status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
         if (status != EFI_SUCCESS)
-                goto free_handle;
+                return status;
 
-        first_gop = NULL;
+        rom->data.type = SETUP_PCI;
+        rom->data.len = size - sizeof(struct setup_data);
+        rom->data.next = 0;
+        rom->pcilen = pci->romsize;
+        *__rom = rom;
 
-        nr_gops = size / sizeof(void *);
-        for (i = 0; i < nr_gops; i++) {
-                struct efi_graphics_output_mode_info *info;
-                efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
-                bool conout_found = false;
-                void *dummy;
-                void *h = gop_handle[i];
+        status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+                                 PCI_VENDOR_ID, 1, &(rom->vendor));
+
+        if (status != EFI_SUCCESS)
+                goto free_struct;
+
+        status = efi_early->call(pci->pci.read, pci, EfiPciIoWidthUint16,
+                                 PCI_DEVICE_ID, 1, &(rom->devid));
+
+        if (status != EFI_SUCCESS)
+                goto free_struct;
+
+        status = efi_early->call(pci->get_location, pci, &(rom->segment),
+                                 &(rom->bus), &(rom->device), &(rom->function));
+
+        if (status != EFI_SUCCESS)
+                goto free_struct;
+
+        memcpy(rom->romdata, pci->romimage, pci->romsize);
+        return status;
+
+free_struct:
+        efi_call_early(free_pool, rom);
+        return status;
+
+}
+
+static efi_status_t
+setup_efi_pci64(struct boot_params *params, void **pci_handle,
+                unsigned long size)
+{
+        efi_pci_io_protocol_64 *pci = NULL;
+        efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+        u64 *handles = (u64 *)(unsigned long)pci_handle;
+        efi_status_t status;
+        unsigned long nr_pci;
+        struct setup_data *data;
+        int i;
+
+        data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+        while (data && data->next)
+                data = (struct setup_data *)(unsigned long)data->next;
+
+        nr_pci = size / sizeof(u64);
+        for (i = 0; i < nr_pci; i++) {
+                struct pci_setup_rom *rom = NULL;
+                u64 h = handles[i];
+
+                status = efi_call_early(handle_protocol, h,
+                                        &pci_proto, (void **)&pci);
 
-                status = efi_call_phys3(sys_table->boottime->handle_protocol,
-                                        h, proto, &gop);
                 if (status != EFI_SUCCESS)
                         continue;
 
-                status = efi_call_phys3(sys_table->boottime->handle_protocol,
-                                        h, &conout_proto, &dummy);
+                if (!pci)
+                        continue;
 
-                if (status == EFI_SUCCESS)
-                        conout_found = true;
+                status = __setup_efi_pci64(pci, &rom);
+                if (status != EFI_SUCCESS)
+                        continue;
 
-                status = efi_call_phys4(gop->query_mode, gop,
-                                        gop->mode->mode, &size, &info);
-                if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
-                        /*
-                         * Systems that use the UEFI Console Splitter may
-                         * provide multiple GOP devices, not all of which are
-                         * backed by real hardware. The workaround is to search
-                         * for a GOP implementing the ConOut protocol, and if
-                         * one isn't found, to just fall back to the first GOP.
-                         */
-                        width = info->horizontal_resolution;
-                        height = info->vertical_resolution;
-                        fb_base = gop->mode->frame_buffer_base;
-                        fb_size = gop->mode->frame_buffer_size;
-                        pixel_format = info->pixel_format;
-                        pixel_info = info->pixel_information;
-                        pixels_per_scan_line = info->pixels_per_scan_line;
+                if (data)
+                        data->next = (unsigned long)rom;
+                else
+                        params->hdr.setup_data = (unsigned long)rom;
+
+                data = (struct setup_data *)rom;
 
-                        /*
-                         * Once we've found a GOP supporting ConOut,
-                         * don't bother looking any further.
-                         */
-                        first_gop = gop;
-                        if (conout_found)
-                                break;
-                }
         }
 
-        /* Did we find any GOPs? */
-        if (!first_gop)
+        return status;
+}
+
+static efi_status_t setup_efi_pci(struct boot_params *params)
+{
+        efi_status_t status;
+        void **pci_handle = NULL;
+        efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
+        unsigned long size = 0;
+
+        status = efi_call_early(locate_handle,
+                                EFI_LOCATE_BY_PROTOCOL,
+                                &pci_proto, NULL, &size, pci_handle);
+
+        if (status == EFI_BUFFER_TOO_SMALL) {
+                status = efi_call_early(allocate_pool,
+                                        EFI_LOADER_DATA,
+                                        size, (void **)&pci_handle);
+
+                if (status != EFI_SUCCESS)
+                        return status;
+
+                status = efi_call_early(locate_handle,
+                                        EFI_LOCATE_BY_PROTOCOL, &pci_proto,
+                                        NULL, &size, pci_handle);
+        }
+
+        if (status != EFI_SUCCESS)
                 goto free_handle;
 
-        /* EFI framebuffer */
-        si->orig_video_isVGA = VIDEO_TYPE_EFI;
+        if (efi_early->is64)
+                status = setup_efi_pci64(params, pci_handle, size);
+        else
+                status = setup_efi_pci32(params, pci_handle, size);
 
-        si->lfb_width = width;
-        si->lfb_height = height;
-        si->lfb_base = fb_base;
-        si->pages = 1;
+free_handle:
+        efi_call_early(free_pool, pci_handle);
+        return status;
+}
 
+static void
+setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line,
+                 struct efi_pixel_bitmask pixel_info, int pixel_format)
+{
         if (pixel_format == PIXEL_RGB_RESERVED_8BIT_PER_COLOR) {
                 si->lfb_depth = 32;
                 si->lfb_linelength = pixels_per_scan_line * 4;
@@ -297,62 +601,319 @@ static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
                 si->rsvd_size = 0;
                 si->rsvd_pos = 0;
         }
+}
+
+static efi_status_t
+__gop_query32(struct efi_graphics_output_protocol_32 *gop32,
+              struct efi_graphics_output_mode_info **info,
+              unsigned long *size, u32 *fb_base)
+{
+        struct efi_graphics_output_protocol_mode_32 *mode;
+        efi_status_t status;
+        unsigned long m;
+
+        m = gop32->mode;
+        mode = (struct efi_graphics_output_protocol_mode_32 *)m;
+
+        status = efi_early->call(gop32->query_mode, gop32,
+                                 mode->mode, size, info);
+        if (status != EFI_SUCCESS)
+                return status;
+
+        *fb_base = mode->frame_buffer_base;
+        return status;
+}
+
+static efi_status_t
+setup_gop32(struct screen_info *si, efi_guid_t *proto,
+            unsigned long size, void **gop_handle)
+{
+        struct efi_graphics_output_protocol_32 *gop32, *first_gop;
+        unsigned long nr_gops;
+        u16 width, height;
+        u32 pixels_per_scan_line;
+        u32 fb_base;
+        struct efi_pixel_bitmask pixel_info;
+        int pixel_format;
+        efi_status_t status;
+        u32 *handles = (u32 *)(unsigned long)gop_handle;
+        int i;
+
+        first_gop = NULL;
+        gop32 = NULL;
+
+        nr_gops = size / sizeof(u32);
+        for (i = 0; i < nr_gops; i++) {
+                struct efi_graphics_output_mode_info *info = NULL;
+                efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
+                bool conout_found = false;
+                void *dummy = NULL;
+                u32 h = handles[i];
+
+                status = efi_call_early(handle_protocol, h,
+                                        proto, (void **)&gop32);
+                if (status != EFI_SUCCESS)
+                        continue;
+
+                status = efi_call_early(handle_protocol, h,
+                                        &conout_proto, &dummy);
+                if (status == EFI_SUCCESS)
+                        conout_found = true;
+
+                status = __gop_query32(gop32, &info, &size, &fb_base);
+                if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+                        /*
+                         * Systems that use the UEFI Console Splitter may
+                         * provide multiple GOP devices, not all of which are
+                         * backed by real hardware. The workaround is to search
+                         * for a GOP implementing the ConOut protocol, and if
+                         * one isn't found, to just fall back to the first GOP.
+                         */
+                        width = info->horizontal_resolution;
+                        height = info->vertical_resolution;
+                        pixel_format = info->pixel_format;
+                        pixel_info = info->pixel_information;
+                        pixels_per_scan_line = info->pixels_per_scan_line;
+
+                        /*
+                         * Once we've found a GOP supporting ConOut,
+                         * don't bother looking any further.
+                         */
+                        first_gop = gop32;
+                        if (conout_found)
+                                break;
+                }
+        }
+
+        /* Did we find any GOPs? */
+        if (!first_gop)
+                goto out;
+
+        /* EFI framebuffer */
+        si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+        si->lfb_width = width;
+        si->lfb_height = height;
+        si->lfb_base = fb_base;
+        si->pages = 1;
+
+        setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
 
         si->lfb_size = si->lfb_linelength * si->lfb_height;
 
         si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
+out:
+        return status;
+}
 
-free_handle:
-        efi_call_phys1(sys_table->boottime->free_pool, gop_handle);
+static efi_status_t
+__gop_query64(struct efi_graphics_output_protocol_64 *gop64,
+              struct efi_graphics_output_mode_info **info,
+              unsigned long *size, u32 *fb_base)
+{
+        struct efi_graphics_output_protocol_mode_64 *mode;
+        efi_status_t status;
+        unsigned long m;
+
+        m = gop64->mode;
+        mode = (struct efi_graphics_output_protocol_mode_64 *)m;
+
+        status = efi_early->call(gop64->query_mode, gop64,
+                                 mode->mode, size, info);
+        if (status != EFI_SUCCESS)
+                return status;
+
+        *fb_base = mode->frame_buffer_base;
+        return status;
+}
+
+static efi_status_t
+setup_gop64(struct screen_info *si, efi_guid_t *proto,
+            unsigned long size, void **gop_handle)
+{
+        struct efi_graphics_output_protocol_64 *gop64, *first_gop;
+        unsigned long nr_gops;
+        u16 width, height;
+        u32 pixels_per_scan_line;
+        u32 fb_base;
+        struct efi_pixel_bitmask pixel_info;
+        int pixel_format;
+        efi_status_t status;
+        u64 *handles = (u64 *)(unsigned long)gop_handle;
+        int i;
+
+        first_gop = NULL;
+        gop64 = NULL;
+
+        nr_gops = size / sizeof(u64);
+        for (i = 0; i < nr_gops; i++) {
+                struct efi_graphics_output_mode_info *info = NULL;
+                efi_guid_t conout_proto = EFI_CONSOLE_OUT_DEVICE_GUID;
+                bool conout_found = false;
+                void *dummy = NULL;
+                u64 h = handles[i];
+
+                status = efi_call_early(handle_protocol, h,
+                                        proto, (void **)&gop64);
+                if (status != EFI_SUCCESS)
+                        continue;
+
+                status = efi_call_early(handle_protocol, h,
+                                        &conout_proto, &dummy);
+                if (status == EFI_SUCCESS)
+                        conout_found = true;
+
+                status = __gop_query64(gop64, &info, &size, &fb_base);
+                if (status == EFI_SUCCESS && (!first_gop || conout_found)) {
+                        /*
+                         * Systems that use the UEFI Console Splitter may
+                         * provide multiple GOP devices, not all of which are
+                         * backed by real hardware. The workaround is to search
+                         * for a GOP implementing the ConOut protocol, and if
+                         * one isn't found, to just fall back to the first GOP.
+                         */
+                        width = info->horizontal_resolution;
+                        height = info->vertical_resolution;
+                        pixel_format = info->pixel_format;
+                        pixel_info = info->pixel_information;
+                        pixels_per_scan_line = info->pixels_per_scan_line;
+
+                        /*
+                         * Once we've found a GOP supporting ConOut,
+                         * don't bother looking any further.
+                         */
+                        first_gop = gop64;
+                        if (conout_found)
+                                break;
+                }
+        }
+
+        /* Did we find any GOPs? */
+        if (!first_gop)
+                goto out;
+
+        /* EFI framebuffer */
+        si->orig_video_isVGA = VIDEO_TYPE_EFI;
+
+        si->lfb_width = width;
+        si->lfb_height = height;
+        si->lfb_base = fb_base;
+        si->pages = 1;
+
+        setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format);
+
+        si->lfb_size = si->lfb_linelength * si->lfb_height;
+
+        si->capabilities |= VIDEO_CAPABILITY_SKIP_QUIRKS;
+out:
         return status;
 }
 
 /*
- * See if we have Universal Graphics Adapter (UGA) protocol
+ * See if we have Graphics Output Protocol
  */
-static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
+static efi_status_t setup_gop(struct screen_info *si, efi_guid_t *proto,
                               unsigned long size)
 {
-        struct efi_uga_draw_protocol *uga, *first_uga;
-        unsigned long nr_ugas;
         efi_status_t status;
-        u32 width, height;
-        void **uga_handle = NULL;
-        int i;
+        void **gop_handle = NULL;
 
-        status = efi_call_phys3(sys_table->boottime->allocate_pool,
-                                EFI_LOADER_DATA, size, &uga_handle);
+        status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+                                size, (void **)&gop_handle);
         if (status != EFI_SUCCESS)
                 return status;
 
-        status = efi_call_phys5(sys_table->boottime->locate_handle,
-                                EFI_LOCATE_BY_PROTOCOL, uga_proto,
-                                NULL, &size, uga_handle);
+        status = efi_call_early(locate_handle,
+                                EFI_LOCATE_BY_PROTOCOL,
+                                proto, NULL, &size, gop_handle);
         if (status != EFI_SUCCESS)
                 goto free_handle;
 
+        if (efi_early->is64)
+                status = setup_gop64(si, proto, size, gop_handle);
+        else
+                status = setup_gop32(si, proto, size, gop_handle);
+
+free_handle:
+        efi_call_early(free_pool, gop_handle);
+        return status;
+}
+
+static efi_status_t
+setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+{
+        struct efi_uga_draw_protocol *uga = NULL, *first_uga;
+        efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+        unsigned long nr_ugas;
+        u32 *handles = (u32 *)uga_handle;;
+        efi_status_t status;
+        int i;
+
         first_uga = NULL;
+        nr_ugas = size / sizeof(u32);
+        for (i = 0; i < nr_ugas; i++) {
+                efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
+                u32 w, h, depth, refresh;
+                void *pciio;
+                u32 handle = handles[i];
+
+                status = efi_call_early(handle_protocol, handle,
+                                        &uga_proto, (void **)&uga);
+                if (status != EFI_SUCCESS)
+                        continue;
+
+                efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
+
+                status = efi_early->call((unsigned long)uga->get_mode, uga,
+                                         &w, &h, &depth, &refresh);
+                if (status == EFI_SUCCESS && (!first_uga || pciio)) {
+                        *width = w;
+                        *height = h;
+
+                        /*
+                         * Once we've found a UGA supporting PCIIO,
+                         * don't bother looking any further.
+                         */
+                        if (pciio)
+                                break;
 
-        nr_ugas = size / sizeof(void *);
+                        first_uga = uga;
+                }
+        }
+
+        return status;
+}
+
+static efi_status_t
+setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+{
+        struct efi_uga_draw_protocol *uga = NULL, *first_uga;
+        efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
+        unsigned long nr_ugas;
+        u64 *handles = (u64 *)uga_handle;;
+        efi_status_t status;
+        int i;
+
+        first_uga = NULL;
+        nr_ugas = size / sizeof(u64);
         for (i = 0; i < nr_ugas; i++) {
                 efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
-                void *handle = uga_handle[i];
                 u32 w, h, depth, refresh;
                 void *pciio;
+                u64 handle = handles[i];
 
-                status = efi_call_phys3(sys_table->boottime->handle_protocol,
-                                        handle, uga_proto, &uga);
+                status = efi_call_early(handle_protocol, handle,
+                                        &uga_proto, (void **)&uga);
                 if (status != EFI_SUCCESS)
                         continue;
 
-                efi_call_phys3(sys_table->boottime->handle_protocol,
-                               handle, &pciio_proto, &pciio);
+                efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
 
-                status = efi_call_phys5(uga->get_mode, uga, &w, &h,
-                                        &depth, &refresh);
+                status = efi_early->call((unsigned long)uga->get_mode, uga,
+                                         &w, &h, &depth, &refresh);
                 if (status == EFI_SUCCESS && (!first_uga || pciio)) {
-                        width = w;
-                        height = h;
+                        *width = w;
+                        *height = h;
 
                         /*
                          * Once we've found a UGA supporting PCIIO,
@@ -365,7 +926,39 @@ static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
                 }
         }
 
-        if (!first_uga)
+        return status;
+}
+
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
+static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
+                              unsigned long size)
+{
+        efi_status_t status;
+        u32 width, height;
+        void **uga_handle = NULL;
+
+        status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+                                size, (void **)&uga_handle);
+        if (status != EFI_SUCCESS)
+                return status;
+
+        status = efi_call_early(locate_handle,
+                                EFI_LOCATE_BY_PROTOCOL,
+                                uga_proto, NULL, &size, uga_handle);
+        if (status != EFI_SUCCESS)
+                goto free_handle;
+
+        height = 0;
+        width = 0;
+
+        if (efi_early->is64)
+                status = setup_uga64(uga_handle, size, &width, &height);
+        else
+                status = setup_uga32(uga_handle, size, &width, &height);
+
+        if (!width && !height)
                 goto free_handle;
 
         /* EFI framebuffer */
@@ -384,9 +977,8 @@ static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
         si->rsvd_size = 8;
         si->rsvd_pos = 24;
 
-
 free_handle:
-        efi_call_phys1(sys_table->boottime->free_pool, uga_handle);
+        efi_call_early(free_pool, uga_handle);
         return status;
 }
 
@@ -404,29 +996,28 @@ void setup_graphics(struct boot_params *boot_params)
         memset(si, 0, sizeof(*si));
 
         size = 0;
-        status = efi_call_phys5(sys_table->boottime->locate_handle,
-                                EFI_LOCATE_BY_PROTOCOL, &graphics_proto,
-                                NULL, &size, gop_handle);
+        status = efi_call_early(locate_handle,
+                                EFI_LOCATE_BY_PROTOCOL,
+                                &graphics_proto, NULL, &size, gop_handle);
         if (status == EFI_BUFFER_TOO_SMALL)
                 status = setup_gop(si, &graphics_proto, size);
 
         if (status != EFI_SUCCESS) {
                 size = 0;
-                status = efi_call_phys5(sys_table->boottime->locate_handle,
-                                        EFI_LOCATE_BY_PROTOCOL, &uga_proto,
-                                        NULL, &size, uga_handle);
+                status = efi_call_early(locate_handle,
+                                        EFI_LOCATE_BY_PROTOCOL,
+                                        &uga_proto, NULL, &size, uga_handle);
                 if (status == EFI_BUFFER_TOO_SMALL)
                         setup_uga(si, &uga_proto, size);
         }
 }
 
-
 /*
  * Because the x86 boot code expects to be passed a boot_params we
  * need to create one ourselves (usually the bootloader would create
  * one for us).
  */
-struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
+struct boot_params *make_boot_params(struct efi_config *c)
 {
         struct boot_params *boot_params;
         struct sys_desc_table *sdt;
@@ -434,7 +1025,7 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
         struct setup_header *hdr;
         struct efi_info *efi;
         efi_loaded_image_t *image;
-        void *options;
+        void *options, *handle;
         efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
         int options_size = 0;
         efi_status_t status;
@@ -445,14 +1036,21 @@ struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
         unsigned long ramdisk_addr;
         unsigned long ramdisk_size;
 
-        sys_table = _table;
+        efi_early = c;
+        sys_table = (efi_system_table_t *)(unsigned long)efi_early->table;
+        handle = (void *)(unsigned long)efi_early->image_handle;
 
         /* Check if we were booted by the EFI firmware */
         if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
                 return NULL;
 
-        status = efi_call_phys3(sys_table->boottime->handle_protocol,
-                                handle, &proto, (void *)&image);
+        if (efi_early->is64)
+                setup_boot_services64(efi_early);
+        else
+                setup_boot_services32(efi_early);
+
+        status = efi_call_early(handle_protocol, handle,
+                                &proto, (void *)&image);
         if (status != EFI_SUCCESS) {
                 efi_printk(sys_table, "Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
                 return NULL;
@@ -641,14 +1239,13 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
                 sizeof(struct e820entry) * nr_desc;
 
         if (*e820ext) {
-                efi_call_phys1(sys_table->boottime->free_pool, *e820ext);
+                efi_call_early(free_pool, *e820ext);
                 *e820ext = NULL;
                 *e820ext_size = 0;
         }
 
-        status = efi_call_phys3(sys_table->boottime->allocate_pool,
-                                EFI_LOADER_DATA, size, e820ext);
-
+        status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+                                size, (void **)e820ext);
         if (status == EFI_SUCCESS)
                 *e820ext_size = size;
 
@@ -656,12 +1253,13 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
 }
 
 static efi_status_t exit_boot(struct boot_params *boot_params,
-                              void *handle)
+                              void *handle, bool is64)
 {
         struct efi_info *efi = &boot_params->efi_info;
         unsigned long map_sz, key, desc_size;
         efi_memory_desc_t *mem_map;
         struct setup_data *e820ext;
+        const char *signature;
         __u32 e820ext_size;
         __u32 nr_desc, prev_nr_desc;
         efi_status_t status;
@@ -691,11 +1289,13 @@ get_map:
                 if (status != EFI_SUCCESS)
                         goto free_mem_map;
 
-                efi_call_phys1(sys_table->boottime->free_pool, mem_map);
+                efi_call_early(free_pool, mem_map);
                 goto get_map; /* Allocated memory, get map again */
         }
 
-        memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
+        signature = is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+        memcpy(&efi->efi_loader_signature, signature, sizeof(__u32));
+
         efi->efi_systab = (unsigned long)sys_table;
         efi->efi_memdesc_size = desc_size;
         efi->efi_memdesc_version = desc_version;
@@ -708,8 +1308,7 @@ get_map:
 #endif
 
         /* Might as well exit boot services now */
-        status = efi_call_phys2(sys_table->boottime->exit_boot_services,
-                                handle, key);
+        status = efi_call_early(exit_boot_services, handle, key);
         if (status != EFI_SUCCESS) {
                 /*
                  * ExitBootServices() will fail if any of the event
@@ -722,7 +1321,7 @@ get_map:
                         goto free_mem_map;
 
                 called_exit = true;
-                efi_call_phys1(sys_table->boottime->free_pool, mem_map);
+                efi_call_early(free_pool, mem_map);
                 goto get_map;
         }
 
@@ -736,23 +1335,31 @@ get_map:
         return EFI_SUCCESS;
 
 free_mem_map:
-        efi_call_phys1(sys_table->boottime->free_pool, mem_map);
+        efi_call_early(free_pool, mem_map);
         return status;
 }
 
-
 /*
  * On success we return a pointer to a boot_params structure, and NULL
  * on failure.
  */
-struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
+struct boot_params *efi_main(struct efi_config *c,
                              struct boot_params *boot_params)
 {
-        struct desc_ptr *gdt;
+        struct desc_ptr *gdt = NULL;
         efi_loaded_image_t *image;
         struct setup_header *hdr = &boot_params->hdr;
         efi_status_t status;
         struct desc_struct *desc;
+        void *handle;
+        efi_system_table_t *_table;
+        bool is64;
+
+        efi_early = c;
+
+        _table = (efi_system_table_t *)(unsigned long)efi_early->table;
+        handle = (void *)(unsigned long)efi_early->image_handle;
+        is64 = efi_early->is64;
 
         sys_table = _table;
 
@@ -760,13 +1367,17 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
         if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
                 goto fail;
 
+        if (is64)
+                setup_boot_services64(efi_early);
+        else
+                setup_boot_services32(efi_early);
+
         setup_graphics(boot_params);
 
         setup_efi_pci(boot_params);
 
-        status = efi_call_phys3(sys_table->boottime->allocate_pool,
-                                EFI_LOADER_DATA, sizeof(*gdt),
-                                (void **)&gdt);
+        status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+                                sizeof(*gdt), (void **)&gdt);
         if (status != EFI_SUCCESS) {
                 efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
                 goto fail;
@@ -797,7 +1408,7 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
                 hdr->code32_start = bzimage_addr;
         }
 
-        status = exit_boot(boot_params, handle);
+        status = exit_boot(boot_params, handle, is64);
         if (status != EFI_SUCCESS)
                 goto fail;
 
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index 81b6b652b46a..c88c31ecad12 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -37,6 +37,24 @@ struct efi_graphics_output_mode_info {
         u32 pixels_per_scan_line;
 } __packed;
 
+struct efi_graphics_output_protocol_mode_32 {
+        u32 max_mode;
+        u32 mode;
+        u32 info;
+        u32 size_of_info;
+        u64 frame_buffer_base;
+        u32 frame_buffer_size;
+} __packed;
+
+struct efi_graphics_output_protocol_mode_64 {
+        u32 max_mode;
+        u32 mode;
+        u64 info;
+        u64 size_of_info;
+        u64 frame_buffer_base;
+        u64 frame_buffer_size;
+} __packed;
+
 struct efi_graphics_output_protocol_mode {
         u32 max_mode;
         u32 mode;
@@ -46,6 +64,20 @@ struct efi_graphics_output_protocol_mode {
         unsigned long frame_buffer_size;
 } __packed;
 
+struct efi_graphics_output_protocol_32 {
+        u32 query_mode;
+        u32 set_mode;
+        u32 blt;
+        u32 mode;
+};
+
+struct efi_graphics_output_protocol_64 {
+        u64 query_mode;
+        u64 set_mode;
+        u64 blt;
+        u64 mode;
+};
+
 struct efi_graphics_output_protocol {
         void *query_mode;
         unsigned long set_mode;
@@ -53,10 +85,38 @@ struct efi_graphics_output_protocol {
         struct efi_graphics_output_protocol_mode *mode;
 };
 
+struct efi_uga_draw_protocol_32 {
+        u32 get_mode;
+        u32 set_mode;
+        u32 blt;
+};
+
+struct efi_uga_draw_protocol_64 {
+        u64 get_mode;
+        u64 set_mode;
+        u64 blt;
+};
+
 struct efi_uga_draw_protocol {
         void *get_mode;
         void *set_mode;
         void *blt;
 };
 
+struct efi_config {
+        u64 image_handle;
+        u64 table;
+        u64 allocate_pool;
+        u64 allocate_pages;
+        u64 get_memory_map;
+        u64 free_pool;
+        u64 free_pages;
+        u64 locate_handle;
+        u64 handle_protocol;
+        u64 exit_boot_services;
+        u64 text_output;
+        efi_status_t (*call)(unsigned long, ...);
+        bool is64;
+} __packed;
+
 #endif /* BOOT_COMPRESSED_EBOOT_H */
diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S
index cedc60de86eb..7ff3632806b1 100644
--- a/arch/x86/boot/compressed/efi_stub_64.S
+++ b/arch/x86/boot/compressed/efi_stub_64.S
@@ -1 +1,30 @@
+#include <asm/segment.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+
 #include "../../platform/efi/efi_stub_64.S"
+
+#ifdef CONFIG_EFI_MIXED
+        .code64
+        .text
+ENTRY(efi64_thunk)
+        push    %rbp
+        push    %rbx
+
+        subq    $16, %rsp
+        leaq    efi_exit32(%rip), %rax
+        movl    %eax, 8(%rsp)
+        leaq    efi_gdt64(%rip), %rax
+        movl    %eax, 4(%rsp)
+        movl    %eax, 2(%rax)           /* Fixup the gdt base address */
+        leaq    efi32_boot_gdt(%rip), %rax
+        movl    %eax, (%rsp)
+
+        call    __efi64_thunk
+
+        addq    $16, %rsp
+        pop     %rbx
+        pop     %rbp
+        ret
+ENDPROC(efi64_thunk)
+#endif /* CONFIG_EFI_MIXED */
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 9116aac232c7..de9d4200d305 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -42,26 +42,53 @@ ENTRY(startup_32)
 ENTRY(efi_pe_entry)
         add     $0x4, %esp
 
+        call    1f
+1:      popl    %esi
+        subl    $1b, %esi
+
+        popl    %ecx
+        movl    %ecx, efi32_config(%esi)        /* Handle */
+        popl    %ecx
+        movl    %ecx, efi32_config+8(%esi)      /* EFI System table pointer */
+
+        /* Relocate efi_config->call() */
+        leal    efi32_config(%esi), %eax
+        add     %esi, 88(%eax)
+        pushl   %eax
+
         call    make_boot_params
         cmpl    $0, %eax
-        je      1f
-        movl    0x4(%esp), %esi
-        movl    (%esp), %ecx
+        je      fail
+        popl    %ecx
         pushl   %eax
-        pushl   %esi
         pushl   %ecx
-        sub     $0x4, %esp
+        jmp     2f              /* Skip efi_config initialization */
 
-ENTRY(efi_stub_entry)
+ENTRY(efi32_stub_entry)
         add     $0x4, %esp
+        popl    %ecx
+        popl    %edx
+
+        call    1f
+1:      popl    %esi
+        subl    $1b, %esi
+
+        movl    %ecx, efi32_config(%esi)        /* Handle */
+        movl    %edx, efi32_config+8(%esi)      /* EFI System table pointer */
+
+        /* Relocate efi_config->call() */
+        leal    efi32_config(%esi), %eax
+        add     %esi, 88(%eax)
+        pushl   %eax
+2:
         call    efi_main
         cmpl    $0, %eax
         movl    %eax, %esi
         jne     2f
-1:
+fail:
         /* EFI init failed, so hang. */
         hlt
-        jmp     1b
+        jmp     fail
 2:
         call    3f
 3:
@@ -202,6 +229,15 @@ relocated:
         xorl    %ebx, %ebx
         jmp     *%eax
 
+#ifdef CONFIG_EFI_STUB
+        .data
+efi32_config:
+        .fill 11,8,0
+        .long efi_call_phys
+        .long 0
+        .byte 0
+#endif
+
 /*
  * Stack and heap for uncompression
  */
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index c5c1ae0997e7..57e58a5fa210 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -113,7 +113,8 @@ ENTRY(startup_32)
         lgdt    gdt(%ebp)
 
         /* Enable PAE mode */
-        movl    $(X86_CR4_PAE), %eax
+        movl    %cr4, %eax
+        orl     $X86_CR4_PAE, %eax
         movl    %eax, %cr4
 
  /*
@@ -178,6 +179,13 @@ ENTRY(startup_32)
          */
         pushl   $__KERNEL_CS
         leal    startup_64(%ebp), %eax
+#ifdef CONFIG_EFI_MIXED
+        movl    efi32_config(%ebp), %ebx
+        cmp     $0, %ebx
+        jz      1f
+        leal    handover_entry(%ebp), %eax
+1:
+#endif
         pushl   %eax
 
         /* Enter paged protected Mode, activating Long Mode */
@@ -188,6 +196,30 @@ ENTRY(startup_32)
         lret
 ENDPROC(startup_32)
 
+#ifdef CONFIG_EFI_MIXED
+        .org 0x190
+ENTRY(efi32_stub_entry)
+        add     $0x4, %esp              /* Discard return address */
+        popl    %ecx
+        popl    %edx
+        popl    %esi
+
+        leal    (BP_scratch+4)(%esi), %esp
+        call    1f
+1:      pop     %ebp
+        subl    $1b, %ebp
+
+        movl    %ecx, efi32_config(%ebp)
+        movl    %edx, efi32_config+8(%ebp)
+        sgdtl   efi32_boot_gdt(%ebp)
+
+        leal    efi32_config(%ebp), %eax
+        movl    %eax, efi_config(%ebp)
+
+        jmp     startup_32
+ENDPROC(efi32_stub_entry)
+#endif
+
         .code64
         .org 0x200
 ENTRY(startup_64)
@@ -209,26 +241,48 @@ ENTRY(startup_64)
         jmp     preferred_addr
 
 ENTRY(efi_pe_entry)
-        mov     %rcx, %rdi
-        mov     %rdx, %rsi
-        pushq   %rdi
-        pushq   %rsi
+        movq    %rcx, efi64_config(%rip)        /* Handle */
+        movq    %rdx, efi64_config+8(%rip) /* EFI System table pointer */
+
+        leaq    efi64_config(%rip), %rax
+        movq    %rax, efi_config(%rip)
+
+        call    1f
+1:      popq    %rbp
+        subq    $1b, %rbp
+
+        /*
+         * Relocate efi_config->call().
+         */
+        addq    %rbp, efi64_config+88(%rip)
+
+        movq    %rax, %rdi
         call    make_boot_params
         cmpq    $0,%rax
-        je      1f
-        mov     %rax, %rdx
-        popq    %rsi
-        popq    %rdi
+        je      fail
+        mov     %rax, %rsi
+        jmp     2f              /* Skip the relocation */
 
-ENTRY(efi_stub_entry)
+handover_entry:
+        call    1f
+1:      popq    %rbp
+        subq    $1b, %rbp
+
+        /*
+         * Relocate efi_config->call().
+         */
+        movq    efi_config(%rip), %rax
+        addq    %rbp, 88(%rax)
+2:
+        movq    efi_config(%rip), %rdi
         call    efi_main
         movq    %rax,%rsi
         cmpq    $0,%rax
         jne     2f
-1:
+fail:
         /* EFI init failed, so hang. */
         hlt
-        jmp     1b
+        jmp     fail
 2:
         call    3f
 3:
@@ -307,6 +361,20 @@ preferred_addr:
         leaq    relocated(%rbx), %rax
         jmp     *%rax
 
+#ifdef CONFIG_EFI_STUB
+        .org 0x390
+ENTRY(efi64_stub_entry)
+        movq    %rdi, efi64_config(%rip)        /* Handle */
+        movq    %rsi, efi64_config+8(%rip) /* EFI System table pointer */
+
+        leaq    efi64_config(%rip), %rax
+        movq    %rax, efi_config(%rip)
+
+        movq    %rdx, %rsi
+        jmp     handover_entry
+ENDPROC(efi64_stub_entry)
+#endif
+
         .text
 relocated:
 
@@ -372,6 +440,25 @@ gdt:
         .quad   0x0000000000000000      /* TS continued */
 gdt_end:
 
+#ifdef CONFIG_EFI_STUB
+efi_config:
+        .quad   0
+
+#ifdef CONFIG_EFI_MIXED
+        .global efi32_config
+efi32_config:
+        .fill   11,8,0
+        .quad   efi64_thunk
+        .byte   0
+#endif
+
+        .global efi64_config
+efi64_config:
+        .fill   11,8,0
+        .quad   efi_call6
+        .byte   1
+#endif /* CONFIG_EFI_STUB */
+
 /*
  * Stack and heap for uncompression
  */
diff --git a/arch/x86/boot/cpucheck.c b/arch/x86/boot/cpucheck.c
index 100a9a10076a..f0d0b20fe149 100644
--- a/arch/x86/boot/cpucheck.c
+++ b/arch/x86/boot/cpucheck.c
@@ -67,6 +67,13 @@ static int is_transmeta(void)
                cpu_vendor[2] == A32('M', 'x', '8', '6');
 }
 
+static int is_intel(void)
+{
+        return cpu_vendor[0] == A32('G', 'e', 'n', 'u') &&
+               cpu_vendor[1] == A32('i', 'n', 'e', 'I') &&
+               cpu_vendor[2] == A32('n', 't', 'e', 'l');
+}
+
 /* Returns a bitmask of which words we have error bits in */
 static int check_cpuflags(void)
 {
@@ -153,6 +160,19 @@ int check_cpu(int *cpu_level_ptr, int *req_level_ptr, u32 **err_flags_ptr)
                 asm("wrmsr" : : "a" (eax), "d" (edx), "c" (ecx));
 
                 err = check_cpuflags();
+        } else if (err == 0x01 &&
+                   !(err_flags[0] & ~(1 << X86_FEATURE_PAE)) &&
+                   is_intel() && cpu.level == 6 &&
+                   (cpu.model == 9 || cpu.model == 13)) {
+                /* PAE is disabled on this Pentium M but can be forced */
+                if (cmdline_find_option_bool("forcepae")) {
+                        puts("WARNING: Forcing PAE in CPU flags\n");
+                        set_bit(X86_FEATURE_PAE, cpu.flags);
+                        err = check_cpuflags();
+                }
+                else {
+                        puts("WARNING: PAE disabled. Use parameter 'forcepae' to enable at your own risk!\n");
+                }
         }
 
         if (err_flags_ptr)
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index ec3b8ba68096..0ca9a5c362bc 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -283,7 +283,7 @@ _start:
         # Part 2 of the header, from the old setup.S
 
                 .ascii  "HdrS"          # header signature
-                .word   0x020c          # header version number (>= 0x0105)
+                .word   0x020d          # header version number (>= 0x0105)
                                         # or else old loadlin-1.5 will fail)
                 .globl realmode_swtch
 realmode_swtch: .word   0, 0            # default_switch, SETUPSEG
@@ -350,7 +350,7 @@ cmd_line_ptr:	.long	0		# (Header version 0x0202 or later)
                                         # can be located anywhere in
                                         # low memory 0x10000 or higher.
 
-ramdisk_max:    .long 0x7fffffff
+initrd_addr_max: .long 0x7fffffff
                                         # (Header version 0x0203 or later)
                                         # The highest safe address for
                                         # the contents of an initrd
@@ -375,7 +375,8 @@ xloadflags:
 # define XLF0 0
 #endif
 
-#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64)
+#if defined(CONFIG_RELOCATABLE) && defined(CONFIG_X86_64) && \
+        !defined(CONFIG_EFI_MIXED)
    /* kernel/boot_param/ramdisk could be loaded above 4g */
 # define XLF1 XLF_CAN_BE_LOADED_ABOVE_4G
 #else
@@ -383,10 +384,14 @@ xloadflags:
 #endif
 
 #ifdef CONFIG_EFI_STUB
-# ifdef CONFIG_X86_64
-#  define XLF23 XLF_EFI_HANDOVER_64             /* 64-bit EFI handover ok */
+# ifdef CONFIG_EFI_MIXED
+#  define XLF23 (XLF_EFI_HANDOVER_32|XLF_EFI_HANDOVER_64)
 # else
-#  define XLF23 XLF_EFI_HANDOVER_32             /* 32-bit EFI handover ok */
+#  ifdef CONFIG_X86_64
+#   define XLF23 XLF_EFI_HANDOVER_64            /* 64-bit EFI handover ok */
+#  else
+#   define XLF23 XLF_EFI_HANDOVER_32            /* 32-bit EFI handover ok */
+#  endif
 # endif
 #else
 # define XLF23 0
@@ -426,13 +431,7 @@ pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 #define INIT_SIZE VO_INIT_SIZE
 #endif
 init_size:              .long INIT_SIZE         # kernel initialization size
-handover_offset:
-#ifdef CONFIG_EFI_STUB
-                        .long 0x30              # offset to the handover
-                                                # protocol entry point
-#else
-                        .long 0
-#endif
+handover_offset:        .long 0                 # Filled in by build.c
 
 # End of setup header #####################################################
 
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index 8e15b22391fc..1a2f2121cada 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -53,7 +53,8 @@ int is_big_kernel;
 
 #define PECOFF_RELOC_RESERVE 0x20
 
-unsigned long efi_stub_entry;
+unsigned long efi32_stub_entry;
+unsigned long efi64_stub_entry;
 unsigned long efi_pe_entry;
 unsigned long startup_64;
 
@@ -219,6 +220,52 @@ static void update_pecoff_text(unsigned int text_start, unsigned int file_sz)
         update_pecoff_section_header(".text", text_start, text_sz);
 }
 
+static int reserve_pecoff_reloc_section(int c)
+{
+        /* Reserve 0x20 bytes for .reloc section */
+        memset(buf+c, 0, PECOFF_RELOC_RESERVE);
+        return PECOFF_RELOC_RESERVE;
+}
+
+static void efi_stub_defaults(void)
+{
+        /* Defaults for old kernel */
+#ifdef CONFIG_X86_32
+        efi_pe_entry = 0x10;
+#else
+        efi_pe_entry = 0x210;
+        startup_64 = 0x200;
+#endif
+}
+
+static void efi_stub_entry_update(void)
+{
+        unsigned long addr = efi32_stub_entry;
+
+#ifdef CONFIG_X86_64
+        /* Yes, this is really how we defined it :( */
+        addr = efi64_stub_entry - 0x200;
+#endif
+
+#ifdef CONFIG_EFI_MIXED
+        if (efi32_stub_entry != addr)
+                die("32-bit and 64-bit EFI entry points do not match\n");
+#endif
+        put_unaligned_le32(addr, &buf[0x264]);
+}
+
+#else
+
+static inline void update_pecoff_setup_and_reloc(unsigned int size) {}
+static inline void update_pecoff_text(unsigned int text_start,
+                                      unsigned int file_sz) {}
+static inline void efi_stub_defaults(void) {}
+static inline void efi_stub_entry_update(void) {}
+
+static inline int reserve_pecoff_reloc_section(int c)
+{
+        return 0;
+}
 #endif /* CONFIG_EFI_STUB */
 
 
@@ -250,7 +297,8 @@ static void parse_zoffset(char *fname)
         p = (char *)buf;
 
         while (p && *p) {
-                PARSE_ZOFS(p, efi_stub_entry);
+                PARSE_ZOFS(p, efi32_stub_entry);
+                PARSE_ZOFS(p, efi64_stub_entry);
                 PARSE_ZOFS(p, efi_pe_entry);
                 PARSE_ZOFS(p, startup_64);
 
@@ -271,15 +319,7 @@ int main(int argc, char ** argv)
         void *kernel;
         u32 crc = 0xffffffffUL;
 
-        /* Defaults for old kernel */
-#ifdef CONFIG_X86_32
-        efi_pe_entry = 0x10;
-        efi_stub_entry = 0x30;
-#else
-        efi_pe_entry = 0x210;
-        efi_stub_entry = 0x230;
-        startup_64 = 0x200;
-#endif
+        efi_stub_defaults();
 
         if (argc != 5)
                 usage();
@@ -302,11 +342,7 @@ int main(int argc, char ** argv)
                 die("Boot block hasn't got boot flag (0xAA55)");
         fclose(file);
 
-#ifdef CONFIG_EFI_STUB
-        /* Reserve 0x20 bytes for .reloc section */
-        memset(buf+c, 0, PECOFF_RELOC_RESERVE);
-        c += PECOFF_RELOC_RESERVE;
-#endif
+        c += reserve_pecoff_reloc_section(c);
 
         /* Pad unused space with zeros */
         setup_sectors = (c + 511) / 512;
@@ -315,9 +351,7 @@ int main(int argc, char ** argv)
         i = setup_sectors*512;
         memset(buf+c, 0, i-c);
 
-#ifdef CONFIG_EFI_STUB
         update_pecoff_setup_and_reloc(i);
-#endif
 
         /* Set the default root device */
         put_unaligned_le16(DEFAULT_ROOT_DEV, &buf[508]);
@@ -342,14 +376,9 @@ int main(int argc, char ** argv)
         buf[0x1f1] = setup_sectors-1;
         put_unaligned_le32(sys_size, &buf[0x1f4]);
 
-#ifdef CONFIG_EFI_STUB
         update_pecoff_text(setup_sectors * 512, sz + i + ((sys_size * 16) - sz));
 
-#ifdef CONFIG_X86_64 /* Yes, this is really how we defined it :( */
-        efi_stub_entry -= 0x200;
-#endif
-        put_unaligned_le32(efi_stub_entry, &buf[0x264]);
-#endif
+        efi_stub_entry_update();
 
         crc = partial_crc32(buf, i, crc);
         if (fwrite(buf, 1, i, dest) != i)
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 7f669853317a..4acddc43ee0c 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -5,3 +5,5 @@ genhdr-y += unistd_64.h
 genhdr-y += unistd_x32.h
 
 generic-y += clkdev.h
+generic-y += cputime.h
+generic-y += mcs_spinlock.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1d2091a226bc..19b0ebafcd3e 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -93,9 +93,6 @@ static inline int is_vsmp_box(void)
         return 0;
 }
 #endif
-extern void xapic_wait_icr_idle(void);
-extern u32 safe_xapic_wait_icr_idle(void);
-extern void xapic_icr_write(u32, u32);
 extern int setup_profiling_timer(unsigned int);
 
 static inline void native_apic_mem_write(u32 reg, u32 v)
@@ -184,7 +181,6 @@ extern int x2apic_phys;
 extern int x2apic_preenabled;
 extern void check_x2apic(void);
 extern void enable_x2apic(void);
-extern void x2apic_icr_write(u32 low, u32 id);
 static inline int x2apic_enabled(void)
 {
         u64 msr;
@@ -221,7 +217,6 @@ static inline void x2apic_force_phys(void)
 {
 }
 
-#define nox2apic        0
 #define x2apic_preenabled 0
 #define x2apic_supported()      0
 #endif
@@ -351,7 +346,7 @@ struct apic {
         int trampoline_phys_low;
         int trampoline_phys_high;
 
-        void (*wait_for_init_deassert)(atomic_t *deassert);
+        bool wait_for_init_deassert;
         void (*smp_callin_clear_local_apic)(void);
         void (*inquire_remote_apic)(int apicid);
 
@@ -517,13 +512,6 @@ extern int default_cpu_present_to_apicid(int mps_cpu);
 extern int default_check_phys_apicid_present(int phys_apicid);
 #endif
 
-static inline void default_wait_for_init_deassert(atomic_t *deassert)
-{
-        while (!atomic_read(deassert))
-                cpu_relax();
-        return;
-}
-
 extern void generic_bigsmp_probe(void);
 
 
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 04a48903b2eb..69bbb4845020 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -85,11 +85,7 @@
 #else
 # define smp_rmb()      barrier()
 #endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb()      wmb()
-#else
-# define smp_wmb()      barrier()
-#endif
+#define smp_wmb()       barrier()
 #define smp_read_barrier_depends()      read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
@@ -100,7 +96,7 @@
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
 #endif /* SMP */
 
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
 
 /*
  * For either of these options x86 doesn't have a strong TSO memory
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index e099f9502ace..63211ef5046a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -37,7 +37,7 @@
 #define X86_FEATURE_PAT         (0*32+16) /* Page Attribute Table */
 #define X86_FEATURE_PSE36       (0*32+17) /* 36-bit PSEs */
 #define X86_FEATURE_PN          (0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH      (0*32+19) /* "clflush" CLFLUSH instruction */
+#define X86_FEATURE_CLFLUSH     (0*32+19) /* CLFLUSH instruction */
 #define X86_FEATURE_DS          (0*32+21) /* "dts" Debug Store */
 #define X86_FEATURE_ACPI        (0*32+22) /* ACPI via MSR */
 #define X86_FEATURE_MMX         (0*32+23) /* Multimedia Extensions */
@@ -217,9 +217,14 @@
 #define X86_FEATURE_INVPCID     (9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM         (9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_MPX         (9*32+14) /* Memory Protection Extension */
+#define X86_FEATURE_AVX512F     (9*32+16) /* AVX-512 Foundation */
 #define X86_FEATURE_RDSEED      (9*32+18) /* The RDSEED instruction */
 #define X86_FEATURE_ADX         (9*32+19) /* The ADCX and ADOX instructions */
 #define X86_FEATURE_SMAP        (9*32+20) /* Supervisor Mode Access Prevention */
+#define X86_FEATURE_CLFLUSHOPT  (9*32+23) /* CLFLUSHOPT instruction */
+#define X86_FEATURE_AVX512PF    (9*32+26) /* AVX-512 Prefetch */
+#define X86_FEATURE_AVX512ER    (9*32+27) /* AVX-512 Exponential and Reciprocal */
+#define X86_FEATURE_AVX512CD    (9*32+28) /* AVX-512 Conflict Detection */
 
 /*
  * BUG word(s)
@@ -313,7 +318,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_pmm_enabled     boot_cpu_has(X86_FEATURE_PMM_EN)
 #define cpu_has_ds              boot_cpu_has(X86_FEATURE_DS)
 #define cpu_has_pebs            boot_cpu_has(X86_FEATURE_PEBS)
-#define cpu_has_clflush         boot_cpu_has(X86_FEATURE_CLFLSH)
+#define cpu_has_clflush         boot_cpu_has(X86_FEATURE_CLFLUSH)
 #define cpu_has_bts             boot_cpu_has(X86_FEATURE_BTS)
 #define cpu_has_gbpages         boot_cpu_has(X86_FEATURE_GBPAGES)
 #define cpu_has_arch_perfmon    boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
diff --git a/arch/x86/include/asm/cputime.h b/arch/x86/include/asm/cputime.h
deleted file mode 100644
index 6d68ad7e0ea3..000000000000
--- a/arch/x86/include/asm/cputime.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/cputime.h>
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 3d6b9f81cc68..0869434eaf72 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -19,9 +19,11 @@
  */
 #define EFI_OLD_MEMMAP          EFI_ARCH_1
 
+#define EFI32_LOADER_SIGNATURE  "EL32"
+#define EFI64_LOADER_SIGNATURE  "EL64"
+
 #ifdef CONFIG_X86_32
 
-#define EFI_LOADER_SIGNATURE    "EL32"
 
 extern unsigned long asmlinkage efi_call_phys(void *, ...);
 
@@ -57,8 +59,6 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 
 #else /* !CONFIG_X86_32 */
 
-#define EFI_LOADER_SIGNATURE    "EL64"
-
 extern u64 efi_call0(void *fp);
 extern u64 efi_call1(void *fp, u64 arg1);
 extern u64 efi_call2(void *fp, u64 arg1, u64 arg2);
@@ -119,7 +119,6 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 #endif /* CONFIG_X86_32 */
 
 extern int add_efi_memmap;
-extern unsigned long x86_efi_facility;
 extern struct efi_scratch efi_scratch;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int efi_memblock_x86_reserve_range(void);
@@ -130,10 +129,13 @@ extern void efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
 extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
-extern void efi_setup_page_tables(void);
+extern int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
+extern void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init old_map_region(efi_memory_desc_t *md);
 extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_mkexec(void);
+extern void __init efi_dump_pagetable(void);
+extern void __init efi_apply_memmap_quirks(void);
 
 struct efi_setup_data {
         u64 fw_vendor;
@@ -152,8 +154,40 @@ static inline bool efi_is_native(void)
         return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
 }
 
+static inline bool efi_runtime_supported(void)
+{
+        if (efi_is_native())
+                return true;
+
+        if (IS_ENABLED(CONFIG_EFI_MIXED) && !efi_enabled(EFI_OLD_MEMMAP))
+                return true;
+
+        return false;
+}
+
 extern struct console early_efi_console;
 extern void parse_efi_setup(u64 phys_addr, u32 data_len);
+
+#ifdef CONFIG_EFI_MIXED
+extern void efi_thunk_runtime_setup(void);
+extern efi_status_t efi_thunk_set_virtual_address_map(
+        void *phys_set_virtual_address_map,
+        unsigned long memory_map_size,
+        unsigned long descriptor_size,
+        u32 descriptor_version,
+        efi_memory_desc_t *virtual_map);
+#else
+static inline void efi_thunk_runtime_setup(void) {}
+static inline efi_status_t efi_thunk_set_virtual_address_map(
+        void *phys_set_virtual_address_map,
+        unsigned long memory_map_size,
+        unsigned long descriptor_size,
+        u32 descriptor_version,
+        efi_memory_desc_t *virtual_map)
+{
+        return EFI_SUCCESS;
+}
+#endif /* CONFIG_EFI_MIXED */
 #else
 /*
  * IF EFI is not configured, have the EFI calls return -ENOSYS.
diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h
index d3d74698dce9..1c7eefe32502 100644
--- a/arch/x86/include/asm/floppy.h
+++ b/arch/x86/include/asm/floppy.h
@@ -145,10 +145,10 @@ static int fd_request_irq(void)
 {
         if (can_use_virtual_dma)
                 return request_irq(FLOPPY_IRQ, floppy_hardint,
-                                   IRQF_DISABLED, "floppy", NULL);
+                                   0, "floppy", NULL);
         else
                 return request_irq(FLOPPY_IRQ, floppy_interrupt,
-                                   IRQF_DISABLED, "floppy", NULL);
+                                   0, "floppy", NULL);
 }
 
 static unsigned long dma_mem_alloc(unsigned long size)
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index ab0ae1aa6d0a..230853da4ec0 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -33,6 +33,9 @@ typedef struct {
 #ifdef CONFIG_X86_MCE_THRESHOLD
         unsigned int irq_threshold_count;
 #endif
+#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
+        unsigned int irq_hv_callback_count;
+#endif
 } ____cacheline_aligned irq_cpustat_t;
 
 DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 34f69cb9350a..91d9c69a629e 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -237,7 +237,7 @@ memcpy_toio(volatile void __iomem *dst, const void *src, size_t count)
 
 static inline void flush_write_buffers(void)
 {
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+#if defined(CONFIG_X86_PPRO_FENCE)
         asm volatile("lock; addl $0,0(%%esp)": : :"memory");
 #endif
 }
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index cd9c41938b8a..c163215abb9a 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_MSHYPER_H
 
 #include <linux/types.h>
+#include <linux/interrupt.h>
 #include <asm/hyperv.h>
 
 struct ms_hyperv_info {
@@ -16,6 +17,7 @@ void hyperv_callback_vector(void);
 #define trace_hyperv_callback_vector hyperv_callback_vector
 #endif
 void hyperv_vector_handler(struct pt_regs *regs);
-void hv_register_vmbus_handler(int irq, irq_handler_t handler);
+void hv_setup_vmbus_irq(void (*handler)(void));
+void hv_remove_vmbus_irq(void);
 
 #endif
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index e139b13f2a33..de36f22eb0b9 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -214,6 +214,8 @@ do {                                                            \
 
 struct msr *msrs_alloc(void);
 void msrs_free(struct msr *msrs);
+int msr_set_bit(u32 msr, u8 bit);
+int msr_clear_bit(u32 msr, u8 bit);
 
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 86f9301903c8..5f2fc4441b11 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -1,6 +1,7 @@
 #ifndef _ASM_X86_NMI_H
 #define _ASM_X86_NMI_H
 
+#include <linux/irq_work.h>
 #include <linux/pm.h>
 #include <asm/irq.h>
 #include <asm/io.h>
@@ -38,6 +39,8 @@ typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *);
 struct nmiaction {
         struct list_head        list;
         nmi_handler_t           handler;
+        u64                     max_duration;
+        struct irq_work         irq_work;
         unsigned long           flags;
         const char              *name;
 };
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5ad38ad07890..b459ddf27d64 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -15,9 +15,10 @@
          : (prot))
 
 #ifndef __ASSEMBLY__
-
 #include <asm/x86_init.h>
 
+void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -445,20 +446,10 @@ static inline int pte_same(pte_t a, pte_t b)
         return a.pte == b.pte;
 }
 
-static inline int pteval_present(pteval_t pteval)
-{
-        /*
-         * Yes Linus, _PAGE_PROTNONE == _PAGE_NUMA. Expressing it this
-         * way clearly states that the intent is that protnone and numa
-         * hinting ptes are considered present for the purposes of
-         * pagetable operations like zapping, protection changes, gup etc.
-         */
-        return pteval & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_NUMA);
-}
-
 static inline int pte_present(pte_t a)
 {
-        return pteval_present(pte_flags(a));
+        return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE |
+                               _PAGE_NUMA);
 }
 
 #define pte_accessible pte_accessible
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 1aa9ccd43223..708f19fb4fc7 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -382,9 +382,13 @@ static inline void update_page_count(int level, unsigned long pages) { }
  * as a pte too.
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+                                    unsigned int *level);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
                                    unsigned numpages, unsigned long page_flags);
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+                               unsigned numpages);
 #endif  /* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index fdedd38fd0fc..a4ea02351f4d 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -449,6 +449,15 @@ struct stack_canary {
 };
 DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
 #endif
+/*
+ * per-CPU IRQ handling stacks
+ */
+struct irq_stack {
+        u32                     stack[THREAD_SIZE/sizeof(u32)];
+} __aligned(THREAD_SIZE);
+
+DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
+DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif  /* X86_64 */
 
 extern unsigned int xstate_size;
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 645cad2c95ff..e820c080a4e9 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -191,6 +191,14 @@ static inline void clflush(volatile void *__p)
         asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
 }
 
+static inline void clflushopt(volatile void *__p)
+{
+        alternative_io(".byte " __stringify(NOP_DS_PREFIX) "; clflush %P0",
+                       ".byte 0x66; clflush %P0",
+                       X86_FEATURE_CLFLUSHOPT,
+                       "+m" (*(volatile char __force *)__p));
+}
+
 #define nop() asm volatile ("nop")
 
 
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index bf156ded74b5..0f62f5482d91 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -26,10 +26,9 @@
 # define LOCK_PTR_REG "D"
 #endif
 
-#if defined(CONFIG_X86_32) && \
-        (defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
+#if defined(CONFIG_X86_32) && (defined(CONFIG_X86_PPRO_FENCE))
 /*
- * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
+ * On PPro SMP, we use a locked operation to unlock
  * (PPro errata 66, 92)
  */
 # define UNLOCK_LOCK_PREFIX LOCK_PREFIX
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index e1940c06ed02..47e5de25ba79 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -9,6 +9,7 @@
 
 #include <linux/compiler.h>
 #include <asm/page.h>
+#include <asm/percpu.h>
 #include <asm/types.h>
 
 /*
@@ -32,12 +33,6 @@ struct thread_info {
         mm_segment_t            addr_limit;
         struct restart_block    restart_block;
         void __user             *sysenter_return;
-#ifdef CONFIG_X86_32
-        unsigned long           previous_esp;   /* ESP of the previous stack in
-                                                   case of nested (IRQ) stacks
-                                                */
-        __u8                    supervisor_stack[0];
-#endif
         unsigned int            sig_on_uaccess_error:1;
         unsigned int            uaccess_err:1;  /* uaccess failed */
 };
@@ -153,9 +148,9 @@ struct thread_info {
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
 
-#ifdef CONFIG_X86_32
+#define STACK_WARN              (THREAD_SIZE/8)
+#define KERNEL_STACK_OFFSET     (5*(BITS_PER_LONG/8))
 
-#define STACK_WARN      (THREAD_SIZE/8)
 /*
  * macros/functions for gaining access to the thread information structure
  *
@@ -163,42 +158,6 @@ struct thread_info {
  */
 #ifndef __ASSEMBLY__
 
-#define current_stack_pointer ({                \
-        unsigned long sp;                       \
-        asm("mov %%esp,%0" : "=g" (sp));        \
-        sp;                                     \
-})
-
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-        return (struct thread_info *)
-                (current_stack_pointer & ~(THREAD_SIZE - 1));
-}
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg)     \
-        movl $-THREAD_SIZE, reg; \
-        andl %esp, reg
-
-/* use this one if reg already contains %esp */
-#define GET_THREAD_INFO_WITH_ESP(reg) \
-        andl $-THREAD_SIZE, reg
-
-#endif
-
-#else /* X86_32 */
-
-#include <asm/percpu.h>
-#define KERNEL_STACK_OFFSET (5*8)
-
-/*
- * macros/functions for gaining access to the thread information structure
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
 DECLARE_PER_CPU(unsigned long, kernel_stack);
 
 static inline struct thread_info *current_thread_info(void)
@@ -213,8 +172,8 @@ static inline struct thread_info *current_thread_info(void)
 
 /* how to get the thread information struct from ASM */
 #define GET_THREAD_INFO(reg) \
-        movq PER_CPU_VAR(kernel_stack),reg ; \
-        subq $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg
+        _ASM_MOV PER_CPU_VAR(kernel_stack),reg ; \
+        _ASM_SUB $(THREAD_SIZE-KERNEL_STACK_OFFSET),reg ;
 
 /*
  * Same if PER_CPU_VAR(kernel_stack) is, perhaps with some offset, already in
@@ -224,8 +183,6 @@ static inline struct thread_info *current_thread_info(void)
 
 #endif
 
-#endif /* !X86_32 */
-
 /*
  * Thread-synchronous status.
  *
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index d35f24e231cd..b28097e4c8c3 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -119,9 +119,10 @@ static inline void setup_node_to_cpumask_map(void) { }
 
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
-#ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)       (cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)                   (cpu_data(cpu).cpu_core_id)
+
+#ifdef ENABLE_TOPO_DEFINES
 #define topology_core_cpumask(cpu)              (per_cpu(cpu_core_map, cpu))
 #define topology_thread_cpumask(cpu)            (per_cpu(cpu_sibling_map, cpu))
 #endif
@@ -133,12 +134,6 @@ static inline void arch_fix_phys_package_id(int num, u32 slot)
 struct pci_bus;
 void x86_pci_root_bus_resources(int bus, struct list_head *resources);
 
-#ifdef CONFIG_SMP
-#define mc_capable()    ((boot_cpu_data.x86_max_cores > 1) && \
-                        (cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids))
-#define smt_capable()                   (smp_num_siblings > 1)
-#endif
-
 #ifdef CONFIG_NUMA
 extern int get_mp_bus_to_node(int busnum);
 extern void set_mp_bus_to_node(int busnum, int node);
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index c2a48139c340..3f556c6a0157 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -23,6 +23,9 @@
 #  include <asm/unistd_64.h>
 #  include <asm/unistd_64_x32.h>
 #  define __ARCH_WANT_COMPAT_SYS_TIME
+#  define __ARCH_WANT_COMPAT_SYS_GETDENTS64
+#  define __ARCH_WANT_COMPAT_SYS_PREADV64
+#  define __ARCH_WANT_COMPAT_SYS_PWRITEV64
 
 # endif
 
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 554738963b28..6c1d7411eb00 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -6,11 +6,14 @@
 
 #define XSTATE_CPUID            0x0000000d
 
-#define XSTATE_FP       0x1
-#define XSTATE_SSE      0x2
-#define XSTATE_YMM      0x4
-#define XSTATE_BNDREGS  0x8
-#define XSTATE_BNDCSR   0x10
+#define XSTATE_FP               0x1
+#define XSTATE_SSE              0x2
+#define XSTATE_YMM              0x4
+#define XSTATE_BNDREGS          0x8
+#define XSTATE_BNDCSR           0x10
+#define XSTATE_OPMASK           0x20
+#define XSTATE_ZMM_Hi256        0x40
+#define XSTATE_Hi16_ZMM         0x80
 
 #define XSTATE_FPSSE    (XSTATE_FP | XSTATE_SSE)
 
@@ -23,7 +26,8 @@
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
 /* Supported features which support lazy state saving */
-#define XSTATE_LAZY     (XSTATE_FP | XSTATE_SSE | XSTATE_YMM)
+#define XSTATE_LAZY     (XSTATE_FP | XSTATE_SSE | XSTATE_YMM                  \
+                        | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
 
 /* Supported features which require eager state saving */
 #define XSTATE_EAGER    (XSTATE_BNDREGS | XSTATE_BNDCSR)
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index c19fc60ff062..4924f4be2b99 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -368,33 +368,58 @@
 #define THERM_LOG_THRESHOLD1           (1 << 9)
 
 /* MISC_ENABLE bits: architectural */
-#define MSR_IA32_MISC_ENABLE_FAST_STRING        (1ULL << 0)
-#define MSR_IA32_MISC_ENABLE_TCC                (1ULL << 1)
-#define MSR_IA32_MISC_ENABLE_EMON               (1ULL << 7)
-#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL        (1ULL << 11)
-#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL       (1ULL << 12)
-#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP (1ULL << 16)
-#define MSR_IA32_MISC_ENABLE_MWAIT              (1ULL << 18)
-#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID        (1ULL << 22)
-#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE       (1ULL << 23)
-#define MSR_IA32_MISC_ENABLE_XD_DISABLE         (1ULL << 34)
+#define MSR_IA32_MISC_ENABLE_FAST_STRING_BIT            0
+#define MSR_IA32_MISC_ENABLE_FAST_STRING                (1ULL << MSR_IA32_MISC_ENABLE_FAST_STRING_BIT)
+#define MSR_IA32_MISC_ENABLE_TCC_BIT                    1
+#define MSR_IA32_MISC_ENABLE_TCC                        (1ULL << MSR_IA32_MISC_ENABLE_TCC_BIT)
+#define MSR_IA32_MISC_ENABLE_EMON_BIT                   7
+#define MSR_IA32_MISC_ENABLE_EMON                       (1ULL << MSR_IA32_MISC_ENABLE_EMON_BIT)
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT            11
+#define MSR_IA32_MISC_ENABLE_BTS_UNAVAIL                (1ULL << MSR_IA32_MISC_ENABLE_BTS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT           12
+#define MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL               (1ULL << MSR_IA32_MISC_ENABLE_PEBS_UNAVAIL_BIT)
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT     16
+#define MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP         (1ULL << MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP_BIT)
+#define MSR_IA32_MISC_ENABLE_MWAIT_BIT                  18
+#define MSR_IA32_MISC_ENABLE_MWAIT                      (1ULL << MSR_IA32_MISC_ENABLE_MWAIT_BIT)
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT            22
+#define MSR_IA32_MISC_ENABLE_LIMIT_CPUID                (1ULL << MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT);
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT           23
+#define MSR_IA32_MISC_ENABLE_XTPR_DISABLE               (1ULL << MSR_IA32_MISC_ENABLE_XTPR_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT             34
+#define MSR_IA32_MISC_ENABLE_XD_DISABLE                 (1ULL << MSR_IA32_MISC_ENABLE_XD_DISABLE_BIT)
 
 /* MISC_ENABLE bits: model-specific, meaning may vary from core to core */
-#define MSR_IA32_MISC_ENABLE_X87_COMPAT         (1ULL << 2)
-#define MSR_IA32_MISC_ENABLE_TM1                (1ULL << 3)
-#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE (1ULL << 4)
-#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE    (1ULL << 6)
-#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK      (1ULL << 8)
-#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE   (1ULL << 9)
-#define MSR_IA32_MISC_ENABLE_FERR               (1ULL << 10)
-#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX     (1ULL << 10)
-#define MSR_IA32_MISC_ENABLE_TM2                (1ULL << 13)
-#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE   (1ULL << 19)
-#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK     (1ULL << 20)
-#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT        (1ULL << 24)
-#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE   (1ULL << 37)
-#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE      (1ULL << 38)
-#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE    (1ULL << 39)
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT             2
+#define MSR_IA32_MISC_ENABLE_X87_COMPAT                 (1ULL << MSR_IA32_MISC_ENABLE_X87_COMPAT_BIT)
+#define MSR_IA32_MISC_ENABLE_TM1_BIT                    3
+#define MSR_IA32_MISC_ENABLE_TM1                        (1ULL << MSR_IA32_MISC_ENABLE_TM1_BIT)
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT     4
+#define MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE         (1ULL << MSR_IA32_MISC_ENABLE_SPLIT_LOCK_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT        6
+#define MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE            (1ULL << MSR_IA32_MISC_ENABLE_L3CACHE_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT          8
+#define MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK              (1ULL << MSR_IA32_MISC_ENABLE_SUPPRESS_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT       9
+#define MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE           (1ULL << MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_BIT                   10
+#define MSR_IA32_MISC_ENABLE_FERR                       (1ULL << MSR_IA32_MISC_ENABLE_FERR_BIT)
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT         10
+#define MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX             (1ULL << MSR_IA32_MISC_ENABLE_FERR_MULTIPLEX_BIT)
+#define MSR_IA32_MISC_ENABLE_TM2_BIT                    13
+#define MSR_IA32_MISC_ENABLE_TM2                        (1ULL << MSR_IA32_MISC_ENABLE_TM2_BIT)
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT       19
+#define MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE           (1ULL << MSR_IA32_MISC_ENABLE_ADJ_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT         20
+#define MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK             (1ULL << MSR_IA32_MISC_ENABLE_SPEEDSTEP_LOCK_BIT)
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT            24
+#define MSR_IA32_MISC_ENABLE_L1D_CONTEXT                (1ULL << MSR_IA32_MISC_ENABLE_L1D_CONTEXT_BIT)
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT       37
+#define MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE           (1ULL << MSR_IA32_MISC_ENABLE_DCU_PREF_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT          38
+#define MSR_IA32_MISC_ENABLE_TURBO_DISABLE              (1ULL << MSR_IA32_MISC_ENABLE_TURBO_DISABLE_BIT)
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT        39
+#define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE            (1ULL << MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE_BIT)
 
 #define MSR_IA32_TSC_DEADLINE           0x000006E0
 
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 1dac94265b59..9f46f2b1cfc2 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -613,10 +613,10 @@ static void acpi_map_cpu2node(acpi_handle handle, int cpu, int physid)
         int nid;
 
         nid = acpi_get_node(handle);
-        if (nid == -1 || !node_online(nid))
-                return;
-        set_apicid_to_node(physid, nid);
-        numa_set_node(cpu, nid);
+        if (nid != -1) {
+                set_apicid_to_node(physid, nid);
+                numa_set_node(cpu, nid);
+        }
 #endif
 }
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index fd972a3e4cbb..9fa8aa051f54 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -18,7 +18,6 @@
 #include <linux/pci_ids.h>
 #include <linux/pci.h>
 #include <linux/bitops.h>
-#include <linux/ioport.h>
 #include <linux/suspend.h>
 #include <asm/e820.h>
 #include <asm/io.h>
@@ -54,18 +53,6 @@ int fallback_aper_force __initdata;
 
 int fix_aperture __initdata = 1;
 
-static struct resource gart_resource = {
-        .name   = "GART",
-        .flags  = IORESOURCE_MEM,
-};
-
-static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
-{
-        gart_resource.start = aper_base;
-        gart_resource.end = aper_base + aper_size - 1;
-        insert_resource(&iomem_resource, &gart_resource);
-}
-
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
@@ -96,7 +83,6 @@ static u32 __init allocate_aperture(void)
         memblock_reserve(addr, aper_size);
         printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
                         aper_size >> 10, addr);
-        insert_aperture_resource((u32)addr, aper_size);
         register_nosave_region(addr >> PAGE_SHIFT,
                                (addr+aper_size) >> PAGE_SHIFT);
 
@@ -444,12 +430,8 @@ int __init gart_iommu_hole_init(void)
 
 out:
         if (!fix && !fallback_aper_force) {
-                if (last_aper_base) {
-                        unsigned long n = (32 * 1024 * 1024) << last_aper_order;
-
-                        insert_aperture_resource((u32)last_aper_base, n);
+                if (last_aper_base)
                         return 1;
-                }
                 return 0;
         }
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 7f26c9a70a9e..53e20531470e 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -133,6 +133,10 @@ static inline void imcr_apic_to_pic(void)
  * +1=force-enable
  */
 static int force_enable_local_apic __initdata;
+
+/* Control whether x2APIC mode is enabled or not */
+static bool nox2apic __initdata;
+
 /*
  * APIC command line parameters
  */
@@ -162,8 +166,7 @@ int x2apic_mode;
 /* x2apic enabled before OS handover */
 int x2apic_preenabled;
 static int x2apic_disabled;
-static int nox2apic;
-static __init int setup_nox2apic(char *str)
+static int __init setup_nox2apic(char *str)
 {
         if (x2apic_enabled()) {
                 int apicid = native_apic_msr_read(APIC_ID);
@@ -178,7 +181,7 @@ static __init int setup_nox2apic(char *str)
         } else
                 setup_clear_cpu_cap(X86_FEATURE_X2APIC);
 
-        nox2apic = 1;
+        nox2apic = true;
 
         return 0;
 }
@@ -283,8 +286,12 @@ u32 native_safe_apic_wait_icr_idle(void)
 
 void native_apic_icr_write(u32 low, u32 id)
 {
+        unsigned long flags;
+
+        local_irq_save(flags);
         apic_write(APIC_ICR2, SET_APIC_DEST_FIELD(id));
         apic_write(APIC_ICR, low);
+        local_irq_restore(flags);
 }
 
 u64 native_apic_icr_read(void)
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index 2c621a6b901a..7c1b29479513 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -198,7 +198,7 @@ static struct apic apic_flat =  {
 
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
-        .wait_for_init_deassert         = NULL,
+        .wait_for_init_deassert         = false,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = default_inquire_remote_apic,
 
@@ -314,7 +314,7 @@ static struct apic apic_physflat =  {
 
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
-        .wait_for_init_deassert         = NULL,
+        .wait_for_init_deassert         = false,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = default_inquire_remote_apic,
 
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index 191ce75c0e54..8c7c98249c20 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -172,8 +172,7 @@ struct apic apic_noop = {
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
 
-        .wait_for_init_deassert         = NULL,
-
+        .wait_for_init_deassert         = false,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = NULL,
 
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 3e67f9e3d7ef..a5b45df8bc88 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -248,7 +248,7 @@ static const struct apic apic_numachip __refconst = {
         .wakeup_secondary_cpu           = numachip_wakeup_secondary,
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
-        .wait_for_init_deassert         = NULL,
+        .wait_for_init_deassert         = false,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = NULL, /* REMRD not supported */
 
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index d50e3640d5ae..e4840aa7a255 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -199,8 +199,7 @@ static struct apic apic_bigsmp = {
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
 
-        .wait_for_init_deassert         = default_wait_for_init_deassert,
-
+        .wait_for_init_deassert         = true,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = default_inquire_remote_apic,
 
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index c55224731b2d..6f8f8b348a39 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -394,12 +394,6 @@ static void es7000_enable_apic_mode(void)
                 WARN(1, "Command failed, status = %x\n", mip_status);
 }
 
-static void es7000_wait_for_init_deassert(atomic_t *deassert)
-{
-        while (!atomic_read(deassert))
-                cpu_relax();
-}
-
 static unsigned int es7000_get_apic_id(unsigned long x)
 {
         return (x >> 24) & 0xFF;
@@ -658,8 +652,7 @@ static struct apic __refdata apic_es7000_cluster = {
         .trampoline_phys_low            = 0x467,
         .trampoline_phys_high           = 0x469,
 
-        .wait_for_init_deassert         = NULL,
-
+        .wait_for_init_deassert         = false,
         /* Nothing to do for most platforms, since cleared by the INIT cycle: */
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = default_inquire_remote_apic,
@@ -722,8 +715,7 @@ static struct apic __refdata apic_es7000 = {
         .trampoline_phys_low            = 0x467,
         .trampoline_phys_high           = 0x469,
 
-        .wait_for_init_deassert         = es7000_wait_for_init_deassert,
-
+        .wait_for_init_deassert         = true,
         /* Nothing to do for most platforms, since cleared by the INIT cycle: */
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = default_inquire_remote_apic,
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index 1e42e8f305ee..030ea1c04f72 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -505,8 +505,7 @@ static struct apic __refdata apic_numaq = {
         .trampoline_phys_high           = NUMAQ_TRAMPOLINE_PHYS_HIGH,
 
         /* We don't do anything here because we use NMI's to boot instead */
-        .wait_for_init_deassert         = NULL,
-
+        .wait_for_init_deassert         = false,
         .smp_callin_clear_local_apic    = numaq_smp_callin_clear_local_apic,
         .inquire_remote_apic            = NULL,
 
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index eb35ef9ee63f..cceb352c968c 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -119,8 +119,7 @@ static struct apic apic_default = {
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
 
-        .wait_for_init_deassert         = default_wait_for_init_deassert,
-
+        .wait_for_init_deassert         = true,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = default_inquire_remote_apic,
 
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index 00146f9b0254..b656128611cd 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -532,8 +532,7 @@ static struct apic apic_summit = {
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
 
-        .wait_for_init_deassert         = default_wait_for_init_deassert,
-
+        .wait_for_init_deassert         = true,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = default_inquire_remote_apic,
 
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index cac85ee6913f..e66766bf1641 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -279,7 +279,7 @@ static struct apic apic_x2apic_cluster = {
 
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
-        .wait_for_init_deassert         = NULL,
+        .wait_for_init_deassert         = false,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = NULL,
 
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index de231e328cae..6d600ebf6c12 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -133,7 +133,7 @@ static struct apic apic_x2apic_phys = {
 
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
-        .wait_for_init_deassert         = NULL,
+        .wait_for_init_deassert         = false,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = NULL,
 
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d263b1307de1..7834389ba5be 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -396,7 +396,7 @@ static struct apic __refdata apic_x2apic_uv_x = {
         .wakeup_secondary_cpu           = uv_wakeup_secondary,
         .trampoline_phys_low            = DEFAULT_TRAMPOLINE_PHYS_LOW,
         .trampoline_phys_high           = DEFAULT_TRAMPOLINE_PHYS_HIGH,
-        .wait_for_init_deassert         = NULL,
+        .wait_for_init_deassert         = false,
         .smp_callin_clear_local_apic    = NULL,
         .inquire_remote_apic            = NULL,
 
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index c67ffa686064..ce8b8ff0e0ef 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -218,7 +218,7 @@ static void amd_k7_smp_check(struct cpuinfo_x86 *c)
          */
         WARN_ONCE(1, "WARNING: This combination of AMD"
                 " processors is not suitable for SMP.\n");
-        add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE);
+        add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
 }
 
 static void init_amd_k7(struct cpuinfo_x86 *c)
@@ -233,9 +233,7 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
         if (c->x86_model >= 6 && c->x86_model <= 10) {
                 if (!cpu_has(c, X86_FEATURE_XMM)) {
                         printk(KERN_INFO "Enabling disabled K7/SSE Support.\n");
-                        rdmsr(MSR_K7_HWCR, l, h);
-                        l &= ~0x00008000;
-                        wrmsr(MSR_K7_HWCR, l, h);
+                        msr_clear_bit(MSR_K7_HWCR, 15);
                         set_cpu_cap(c, X86_FEATURE_XMM);
                 }
         }
@@ -509,14 +507,8 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 #endif
 
         /* F16h erratum 793, CVE-2013-6885 */
-        if (c->x86 == 0x16 && c->x86_model <= 0xf) {
-                u64 val;
-
-                rdmsrl(MSR_AMD64_LS_CFG, val);
-                if (!(val & BIT(15)))
-                        wrmsrl(MSR_AMD64_LS_CFG, val | BIT(15));
-        }
-
+        if (c->x86 == 0x16 && c->x86_model <= 0xf)
+                msr_set_bit(MSR_AMD64_LS_CFG, 15);
 }
 
 static const int amd_erratum_383[];
@@ -536,11 +528,8 @@ static void init_amd(struct cpuinfo_x86 *c)
          * Errata 63 for SH-B3 steppings
          * Errata 122 for all steppings (F+ have it disabled by default)
          */
-        if (c->x86 == 0xf) {
-                rdmsrl(MSR_K7_HWCR, value);
-                value |= 1 << 6;
-                wrmsrl(MSR_K7_HWCR, value);
-        }
+        if (c->x86 == 0xf)
+                msr_set_bit(MSR_K7_HWCR, 6);
 #endif
 
         early_init_amd(c);
@@ -623,14 +612,11 @@ static void init_amd(struct cpuinfo_x86 *c)
             (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
             !cpu_has(c, X86_FEATURE_TOPOEXT)) {
 
-                if (!rdmsrl_safe(0xc0011005, &value)) {
-                        value |= 1ULL << 54;
-                        wrmsrl_safe(0xc0011005, value);
+                if (msr_set_bit(0xc0011005, 54) > 0) {
                         rdmsrl(0xc0011005, value);
-                        if (value & (1ULL << 54)) {
+                        if (value & BIT_64(54)) {
                                 set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-                                printk(KERN_INFO FW_INFO "CPU: Re-enabling "
-                                  "disabled Topology Extensions Support\n");
+                                pr_info(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
                         }
                 }
         }
@@ -709,19 +695,12 @@ static void init_amd(struct cpuinfo_x86 *c)
                  * Disable GART TLB Walk Errors on Fam10h. We do this here
                  * because this is always needed when GART is enabled, even in a
                  * kernel which has no MCE support built in.
-                 * BIOS should disable GartTlbWlk Errors themself. If
-                 * it doesn't do it here as suggested by the BKDG.
+                 * BIOS should disable GartTlbWlk Errors already. If
+                 * it doesn't, do it here as suggested by the BKDG.
                  *
                  * Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=33012
                  */
-                u64 mask;
-                int err;
-
-                err = rdmsrl_safe(MSR_AMD64_MCx_MASK(4), &mask);
-                if (err == 0) {
-                        mask |= (1 << 10);
-                        wrmsrl_safe(MSR_AMD64_MCx_MASK(4), mask);
-                }
+                msr_set_bit(MSR_AMD64_MCx_MASK(4), 10);
 
                 /*
                  * On family 10h BIOS may not have properly enabled WC+ support,
@@ -733,10 +712,7 @@ static void init_amd(struct cpuinfo_x86 *c)
                  * NOTE: we want to use the _safe accessors so as not to #GP kvm
                  * guests on older kvm hosts.
                  */
-
-                rdmsrl_safe(MSR_AMD64_BU_CFG2, &value);
-                value &= ~(1ULL << 24);
-                wrmsrl_safe(MSR_AMD64_BU_CFG2, value);
+                msr_clear_bit(MSR_AMD64_BU_CFG2, 24);
 
                 if (cpu_has_amd_erratum(c, amd_erratum_383))
                         set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH);
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index 8779edab684e..d8fba5c15fbd 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -8,236 +8,6 @@
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_OOSTORE
-
-static u32 power2(u32 x)
-{
-        u32 s = 1;
-
-        while (s <= x)
-                s <<= 1;
-
-        return s >>= 1;
-}
-
-
-/*
- * Set up an actual MCR
- */
-static void centaur_mcr_insert(int reg, u32 base, u32 size, int key)
-{
-        u32 lo, hi;
-
-        hi = base & ~0xFFF;
-        lo = ~(size-1);         /* Size is a power of 2 so this makes a mask */
-        lo &= ~0xFFF;           /* Remove the ctrl value bits */
-        lo |= key;              /* Attribute we wish to set */
-        wrmsr(reg+MSR_IDT_MCR0, lo, hi);
-        mtrr_centaur_report_mcr(reg, lo, hi);   /* Tell the mtrr driver */
-}
-
-/*
- * Figure what we can cover with MCR's
- *
- * Shortcut: We know you can't put 4Gig of RAM on a winchip
- */
-static u32 ramtop(void)
-{
-        u32 clip = 0xFFFFFFFFUL;
-        u32 top = 0;
-        int i;
-
-        for (i = 0; i < e820.nr_map; i++) {
-                unsigned long start, end;
-
-                if (e820.map[i].addr > 0xFFFFFFFFUL)
-                        continue;
-                /*
-                 * Don't MCR over reserved space. Ignore the ISA hole
-                 * we frob around that catastrophe already
-                 */
-                if (e820.map[i].type == E820_RESERVED) {
-                        if (e820.map[i].addr >= 0x100000UL &&
-                            e820.map[i].addr < clip)
-                                clip = e820.map[i].addr;
-                        continue;
-                }
-                start = e820.map[i].addr;
-                end = e820.map[i].addr + e820.map[i].size;
-                if (start >= end)
-                        continue;
-                if (end > top)
-                        top = end;
-        }
-        /*
-         * Everything below 'top' should be RAM except for the ISA hole.
-         * Because of the limited MCR's we want to map NV/ACPI into our
-         * MCR range for gunk in RAM
-         *
-         * Clip might cause us to MCR insufficient RAM but that is an
-         * acceptable failure mode and should only bite obscure boxes with
-         * a VESA hole at 15Mb
-         *
-         * The second case Clip sometimes kicks in is when the EBDA is marked
-         * as reserved. Again we fail safe with reasonable results
-         */
-        if (top > clip)
-                top = clip;
-
-        return top;
-}
-
-/*
- * Compute a set of MCR's to give maximum coverage
- */
-static int centaur_mcr_compute(int nr, int key)
-{
-        u32 mem = ramtop();
-        u32 root = power2(mem);
-        u32 base = root;
-        u32 top = root;
-        u32 floor = 0;
-        int ct = 0;
-
-        while (ct < nr) {
-                u32 fspace = 0;
-                u32 high;
-                u32 low;
-
-                /*
-                 * Find the largest block we will fill going upwards
-                 */
-                high = power2(mem-top);
-
-                /*
-                 * Find the largest block we will fill going downwards
-                 */
-                low = base/2;
-
-                /*
-                 * Don't fill below 1Mb going downwards as there
-                 * is an ISA hole in the way.
-                 */
-                if (base <= 1024*1024)
-                        low = 0;
-
-                /*
-                 * See how much space we could cover by filling below
-                 * the ISA hole
-                 */
-
-                if (floor == 0)
-                        fspace = 512*1024;
-                else if (floor == 512*1024)
-                        fspace = 128*1024;
-
-                /* And forget ROM space */
-
-                /*
-                 * Now install the largest coverage we get
-                 */
-                if (fspace > high && fspace > low) {
-                        centaur_mcr_insert(ct, floor, fspace, key);
-                        floor += fspace;
-                } else if (high > low) {
-                        centaur_mcr_insert(ct, top, high, key);
-                        top += high;
-                } else if (low > 0) {
-                        base -= low;
-                        centaur_mcr_insert(ct, base, low, key);
-                } else
-                        break;
-                ct++;
-        }
-        /*
-         * We loaded ct values. We now need to set the mask. The caller
-         * must do this bit.
-         */
-        return ct;
-}
-
-static void centaur_create_optimal_mcr(void)
-{
-        int used;
-        int i;
-
-        /*
-         * Allocate up to 6 mcrs to mark as much of ram as possible
-         * as write combining and weak write ordered.
-         *
-         * To experiment with: Linux never uses stack operations for
-         * mmio spaces so we could globally enable stack operation wc
-         *
-         * Load the registers with type 31 - full write combining, all
-         * writes weakly ordered.
-         */
-        used = centaur_mcr_compute(6, 31);
-
-        /*
-         * Wipe unused MCRs
-         */
-        for (i = used; i < 8; i++)
-                wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-static void winchip2_create_optimal_mcr(void)
-{
-        u32 lo, hi;
-        int used;
-        int i;
-
-        /*
-         * Allocate up to 6 mcrs to mark as much of ram as possible
-         * as write combining, weak store ordered.
-         *
-         * Load the registers with type 25
-         *      8       -       weak write ordering
-         *      16      -       weak read ordering
-         *      1       -       write combining
-         */
-        used = centaur_mcr_compute(6, 25);
-
-        /*
-         * Mark the registers we are using.
-         */
-        rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-        for (i = 0; i < used; i++)
-                lo |= 1<<(9+i);
-        wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-
-        /*
-         * Wipe unused MCRs
-         */
-
-        for (i = used; i < 8; i++)
-                wrmsr(MSR_IDT_MCR0+i, 0, 0);
-}
-
-/*
- * Handle the MCR key on the Winchip 2.
- */
-static void winchip2_unprotect_mcr(void)
-{
-        u32 lo, hi;
-        u32 key;
-
-        rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-        lo &= ~0x1C0;   /* blank bits 8-6 */
-        key = (lo>>17) & 7;
-        lo |= key<<6;   /* replace with unlock key */
-        wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-
-static void winchip2_protect_mcr(void)
-{
-        u32 lo, hi;
-
-        rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-        lo &= ~0x1C0;   /* blank bits 8-6 */
-        wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-}
-#endif /* CONFIG_X86_OOSTORE */
-
 #define ACE_PRESENT     (1 << 6)
 #define ACE_ENABLED     (1 << 7)
 #define ACE_FCR         (1 << 28)       /* MSR_VIA_FCR */
@@ -362,20 +132,6 @@ static void init_centaur(struct cpuinfo_x86 *c)
                         fcr_clr = DPDC;
                         printk(KERN_NOTICE "Disabling bugged TSC.\n");
                         clear_cpu_cap(c, X86_FEATURE_TSC);
-#ifdef CONFIG_X86_OOSTORE
-                        centaur_create_optimal_mcr();
-                        /*
-                         * Enable:
-                         *      write combining on non-stack, non-string
-                         *      write combining on string, all types
-                         *      weak write ordering
-                         *
-                         * The C6 original lacks weak read order
-                         *
-                         * Note 0x120 is write only on Winchip 1
-                         */
-                        wrmsr(MSR_IDT_MCR_CTRL, 0x01F0001F, 0);
-#endif
                         break;
                 case 8:
                         switch (c->x86_mask) {
@@ -392,40 +148,12 @@ static void init_centaur(struct cpuinfo_x86 *c)
                         fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
                                   E2MMX|EAMD3D;
                         fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
-                        winchip2_unprotect_mcr();
-                        winchip2_create_optimal_mcr();
-                        rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-                        /*
-                         * Enable:
-                         *      write combining on non-stack, non-string
-                         *      write combining on string, all types
-                         *      weak write ordering
-                         */
-                        lo |= 31;
-                        wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-                        winchip2_protect_mcr();
-#endif
                         break;
                 case 9:
                         name = "3";
                         fcr_set = ECX8|DSMC|DTLOCK|EMMX|EBRPRED|ERETSTK|
                                   E2MMX|EAMD3D;
                         fcr_clr = DPDC;
-#ifdef CONFIG_X86_OOSTORE
-                        winchip2_unprotect_mcr();
-                        winchip2_create_optimal_mcr();
-                        rdmsr(MSR_IDT_MCR_CTRL, lo, hi);
-                        /*
-                         * Enable:
-                         *      write combining on non-stack, non-string
-                         *      write combining on string, all types
-                         *      weak write ordering
-                         */
-                        lo |= 31;
-                        wrmsr(MSR_IDT_MCR_CTRL, lo, hi);
-                        winchip2_protect_mcr();
-#endif
                         break;
                 default:
                         name = "??";
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8e28bf2fc3ef..a135239badb7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1025,7 +1025,8 @@ __setup("show_msr=", setup_show_msr);
 
 static __init int setup_noclflush(char *arg)
 {
-        setup_clear_cpu_cap(X86_FEATURE_CLFLSH);
+        setup_clear_cpu_cap(X86_FEATURE_CLFLUSH);
+        setup_clear_cpu_cap(X86_FEATURE_CLFLUSHOPT);
         return 1;
 }
 __setup("noclflush", setup_noclflush);
@@ -1078,6 +1079,10 @@ static __init int setup_disablecpuid(char *arg)
 }
 __setup("clearcpuid=", setup_disablecpuid);
 
+DEFINE_PER_CPU(unsigned long, kernel_stack) =
+        (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
+EXPORT_PER_CPU_SYMBOL(kernel_stack);
+
 #ifdef CONFIG_X86_64
 struct desc_ptr idt_descr = { NR_VECTORS * 16 - 1, (unsigned long) idt_table };
 struct desc_ptr debug_idt_descr = { NR_VECTORS * 16 - 1,
@@ -1094,10 +1099,6 @@ DEFINE_PER_CPU(struct task_struct *, current_task) ____cacheline_aligned =
         &init_task;
 EXPORT_PER_CPU_SYMBOL(current_task);
 
-DEFINE_PER_CPU(unsigned long, kernel_stack) =
-        (unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;
-EXPORT_PER_CPU_SYMBOL(kernel_stack);
-
 DEFINE_PER_CPU(char *, irq_stack_ptr) =
         init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 5cd9bfabd645..897d6201ef10 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -31,11 +31,8 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 
         /* Unmask CPUID levels if masked: */
         if (c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xd)) {
-                rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-
-                if (misc_enable & MSR_IA32_MISC_ENABLE_LIMIT_CPUID) {
-                        misc_enable &= ~MSR_IA32_MISC_ENABLE_LIMIT_CPUID;
-                        wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+                if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
+                                  MSR_IA32_MISC_ENABLE_LIMIT_CPUID_BIT) > 0) {
                         c->cpuid_level = cpuid_eax(0);
                         get_cpu_cap(c);
                 }
@@ -129,16 +126,10 @@ static void early_init_intel(struct cpuinfo_x86 *c)
          * Ingo Molnar reported a Pentium D (model 6) and a Xeon
          * (model 2) with the same problem.
          */
-        if (c->x86 == 15) {
-                rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-
-                if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
-                        printk(KERN_INFO "kmemcheck: Disabling fast string operations\n");
-
-                        misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
-                        wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
-                }
-        }
+        if (c->x86 == 15)
+                if (msr_clear_bit(MSR_IA32_MISC_ENABLE,
+                                  MSR_IA32_MISC_ENABLE_FAST_STRING_BIT) > 0)
+                        pr_info("kmemcheck: Disabling fast string operations\n");
 #endif
 
         /*
@@ -195,10 +186,16 @@ static void intel_smp_check(struct cpuinfo_x86 *c)
         }
 }
 
-static void intel_workarounds(struct cpuinfo_x86 *c)
+static int forcepae;
+static int __init forcepae_setup(char *__unused)
 {
-        unsigned long lo, hi;
+        forcepae = 1;
+        return 1;
+}
+__setup("forcepae", forcepae_setup);
 
+static void intel_workarounds(struct cpuinfo_x86 *c)
+{
 #ifdef CONFIG_X86_F00F_BUG
         /*
          * All current models of Pentium and Pentium with MMX technology CPUs
@@ -225,16 +222,26 @@ static void intel_workarounds(struct cpuinfo_x86 *c)
                 clear_cpu_cap(c, X86_FEATURE_SEP);
 
         /*
+         * PAE CPUID issue: many Pentium M report no PAE but may have a
+         * functionally usable PAE implementation.
+         * Forcefully enable PAE if kernel parameter "forcepae" is present.
+         */
+        if (forcepae) {
+                printk(KERN_WARNING "PAE forced!\n");
+                set_cpu_cap(c, X86_FEATURE_PAE);
+                add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_NOW_UNRELIABLE);
+        }
+
+        /*
          * P4 Xeon errata 037 workaround.
          * Hardware prefetcher may cause stale data to be loaded into the cache.
          */
         if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
-                rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
-                if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) {
-                        printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n");
-                        printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n");
-                        lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE;
-                        wrmsr(MSR_IA32_MISC_ENABLE, lo, hi);
+                if (msr_set_bit(MSR_IA32_MISC_ENABLE,
+                                MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE_BIT)
+                    > 0) {
+                        pr_info("CPU: C0 stepping P4 Xeon detected.\n");
+                        pr_info("CPU: Disabling hardware prefetching (Errata 037)\n");
                 }
         }
 
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 9f7ca266864a..76f98fe5b35c 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -17,6 +17,7 @@
 #include <linux/hardirq.h>
 #include <linux/efi.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <asm/processor.h>
 #include <asm/hypervisor.h>
 #include <asm/hyperv.h>
@@ -26,10 +27,50 @@
 #include <asm/irq_regs.h>
 #include <asm/i8259.h>
 #include <asm/apic.h>
+#include <asm/timer.h>
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
 
+#if IS_ENABLED(CONFIG_HYPERV)
+static void (*vmbus_handler)(void);
+
+void hyperv_vector_handler(struct pt_regs *regs)
+{
+        struct pt_regs *old_regs = set_irq_regs(regs);
+
+        irq_enter();
+        exit_idle();
+
+        inc_irq_stat(irq_hv_callback_count);
+        if (vmbus_handler)
+                vmbus_handler();
+
+        irq_exit();
+        set_irq_regs(old_regs);
+}
+
+void hv_setup_vmbus_irq(void (*handler)(void))
+{
+        vmbus_handler = handler;
+        /*
+         * Setup the IDT for hypervisor callback. Prevent reallocation
+         * at module reload.
+         */
+        if (!test_bit(HYPERVISOR_CALLBACK_VECTOR, used_vectors))
+                alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR,
+                                hyperv_callback_vector);
+}
+
+void hv_remove_vmbus_irq(void)
+{
+        /* We have no way to deallocate the interrupt gate */
+        vmbus_handler = NULL;
+}
+EXPORT_SYMBOL_GPL(hv_setup_vmbus_irq);
+EXPORT_SYMBOL_GPL(hv_remove_vmbus_irq);
+#endif
+
 static uint32_t  __init ms_hyperv_platform(void)
 {
         u32 eax;
@@ -105,6 +146,11 @@ static void __init ms_hyperv_init_platform(void)
 
         if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
                 clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
+
+#ifdef CONFIG_X86_IO_APIC
+        no_timer_check = 1;
+#endif
+
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
@@ -113,41 +159,3 @@ const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
         .init_platform          = ms_hyperv_init_platform,
 };
 EXPORT_SYMBOL(x86_hyper_ms_hyperv);
-
-#if IS_ENABLED(CONFIG_HYPERV)
-static int vmbus_irq = -1;
-static irq_handler_t vmbus_isr;
-
-void hv_register_vmbus_handler(int irq, irq_handler_t handler)
-{
-        /*
-         * Setup the IDT for hypervisor callback.
-         */
-        alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
-
-        vmbus_irq = irq;
-        vmbus_isr = handler;
-}
-
-void hyperv_vector_handler(struct pt_regs *regs)
-{
-        struct pt_regs *old_regs = set_irq_regs(regs);
-        struct irq_desc *desc;
-
-        irq_enter();
-        exit_idle();
-
-        desc = irq_to_desc(vmbus_irq);
-
-        if (desc)
-                generic_handle_irq_desc(vmbus_irq, desc);
-
-        irq_exit();
-        set_irq_regs(old_regs);
-}
-#else
-void hv_register_vmbus_handler(int irq, irq_handler_t handler)
-{
-}
-#endif
-EXPORT_SYMBOL_GPL(hv_register_vmbus_handler);
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 895604f2e916..ae407f7226c8 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -892,7 +892,6 @@ static void x86_pmu_enable(struct pmu *pmu)
                  * hw_perf_group_sched_in() or x86_pmu_enable()
                  *
                  * step1: save events moving to new counters
-                 * step2: reprogram moved events into new counters
                  */
                 for (i = 0; i < n_running; i++) {
                         event = cpuc->event_list[i];
@@ -918,6 +917,9 @@ static void x86_pmu_enable(struct pmu *pmu)
                         x86_pmu_stop(event, PERF_EF_UPDATE);
                 }
 
+                /*
+                 * step2: reprogram moved events into new counters
+                 */
                 for (i = 0; i < cpuc->n_events; i++) {
                         event = cpuc->event_list[i];
                         hwc = &event->hw;
@@ -1043,7 +1045,7 @@ static int x86_pmu_add(struct perf_event *event, int flags)
         /*
          * If group events scheduling transaction was started,
          * skip the schedulability test here, it will be performed
-         * at commit time (->commit_txn) as a whole
+         * at commit time (->commit_txn) as a whole.
          */
         if (cpuc->group_flag & PERF_EVENT_TXN)
                 goto done_collect;
@@ -1058,6 +1060,10 @@ static int x86_pmu_add(struct perf_event *event, int flags)
         memcpy(cpuc->assign, assign, n*sizeof(int));
 
 done_collect:
+        /*
+         * Commit the collect_events() state. See x86_pmu_del() and
+         * x86_pmu_*_txn().
+         */
         cpuc->n_events = n;
         cpuc->n_added += n - n0;
         cpuc->n_txn += n - n0;
@@ -1183,25 +1189,38 @@ static void x86_pmu_del(struct perf_event *event, int flags)
          * If we're called during a txn, we don't need to do anything.
          * The events never got scheduled and ->cancel_txn will truncate
          * the event_list.
+         *
+         * XXX assumes any ->del() called during a TXN will only be on
+         * an event added during that same TXN.
          */
         if (cpuc->group_flag & PERF_EVENT_TXN)
                 return;
 
+        /*
+         * Not a TXN, therefore cleanup properly.
+         */
         x86_pmu_stop(event, PERF_EF_UPDATE);
 
         for (i = 0; i < cpuc->n_events; i++) {
-                if (event == cpuc->event_list[i]) {
+                if (event == cpuc->event_list[i])
+                        break;
+        }
 
-                        if (x86_pmu.put_event_constraints)
-                                x86_pmu.put_event_constraints(cpuc, event);
+        if (WARN_ON_ONCE(i == cpuc->n_events)) /* called ->del() without ->add() ? */
+                return;
 
-                        while (++i < cpuc->n_events)
-                                cpuc->event_list[i-1] = cpuc->event_list[i];
+        /* If we have a newly added event; make sure to decrease n_added. */
+        if (i >= cpuc->n_events - cpuc->n_added)
+                --cpuc->n_added;
+
+        if (x86_pmu.put_event_constraints)
+                x86_pmu.put_event_constraints(cpuc, event);
+
+        /* Delete the array entry. */
+        while (++i < cpuc->n_events)
+                cpuc->event_list[i-1] = cpuc->event_list[i];
+        --cpuc->n_events;
 
-                        --cpuc->n_events;
-                        break;
-                }
-        }
         perf_event_update_userpage(event);
 }
 
@@ -1595,7 +1614,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
 {
         __this_cpu_and(cpu_hw_events.group_flag, ~PERF_EVENT_TXN);
         /*
-         * Truncate the collected events.
+         * Truncate collected array by the number of events added in this
+         * transaction. See x86_pmu_add() and x86_pmu_*_txn().
          */
         __this_cpu_sub(cpu_hw_events.n_added, __this_cpu_read(cpu_hw_events.n_txn));
         __this_cpu_sub(cpu_hw_events.n_events, __this_cpu_read(cpu_hw_events.n_txn));
@@ -1606,6 +1626,8 @@ static void x86_pmu_cancel_txn(struct pmu *pmu)
  * Commit group events scheduling transaction
  * Perform the group schedulability test as a whole
  * Return 0 if success
+ *
+ * Does not cancel the transaction on failure; expects the caller to do this.
  */
 static int x86_pmu_commit_txn(struct pmu *pmu)
 {
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 4972c244d0bc..3b2f9bdd974b 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -130,9 +130,11 @@ struct cpu_hw_events {
         unsigned long           running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
         int                     enabled;
 
-        int                     n_events;
-        int                     n_added;
-        int                     n_txn;
+        int                     n_events; /* the # of events in the below arrays */
+        int                     n_added;  /* the # last events in the below arrays;
+                                             they've never been enabled yet */
+        int                     n_txn;    /* the # last events in the below arrays;
+                                             added in the current transaction */
         int                     assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
         u64                     tags[X86_PMC_IDX_MAX];
         struct perf_event       *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index c88f7f4b03ee..bd2253d40cff 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -66,6 +66,47 @@ DEFINE_UNCORE_FORMAT_ATTR(mask_vnw, mask_vnw, "config2:3-4");
 DEFINE_UNCORE_FORMAT_ATTR(mask0, mask0, "config2:0-31");
 DEFINE_UNCORE_FORMAT_ATTR(mask1, mask1, "config2:32-63");
 
+static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box);
+static void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box);
+static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event);
+static void uncore_pmu_event_read(struct perf_event *event);
+
+static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
+{
+        return container_of(event->pmu, struct intel_uncore_pmu, pmu);
+}
+
+static struct intel_uncore_box *
+uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
+{
+        struct intel_uncore_box *box;
+
+        box = *per_cpu_ptr(pmu->box, cpu);
+        if (box)
+                return box;
+
+        raw_spin_lock(&uncore_box_lock);
+        list_for_each_entry(box, &pmu->box_list, list) {
+                if (box->phys_id == topology_physical_package_id(cpu)) {
+                        atomic_inc(&box->refcnt);
+                        *per_cpu_ptr(pmu->box, cpu) = box;
+                        break;
+                }
+        }
+        raw_spin_unlock(&uncore_box_lock);
+
+        return *per_cpu_ptr(pmu->box, cpu);
+}
+
+static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
+{
+        /*
+         * perf core schedules event on the basis of cpu, uncore events are
+         * collected by one of the cpus inside a physical package.
+         */
+        return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+}
+
 static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
         u64 count;
@@ -1639,6 +1680,349 @@ static struct intel_uncore_type *snb_msr_uncores[] = {
         &snb_uncore_cbox,
         NULL,
 };
+
+enum {
+        SNB_PCI_UNCORE_IMC,
+};
+
+static struct uncore_event_desc snb_uncore_imc_events[] = {
+        INTEL_UNCORE_EVENT_DESC(data_reads,  "event=0x01"),
+        INTEL_UNCORE_EVENT_DESC(data_reads.scale, "6.103515625e-5"),
+        INTEL_UNCORE_EVENT_DESC(data_reads.unit, "MiB"),
+
+        INTEL_UNCORE_EVENT_DESC(data_writes, "event=0x02"),
+        INTEL_UNCORE_EVENT_DESC(data_writes.scale, "6.103515625e-5"),
+        INTEL_UNCORE_EVENT_DESC(data_writes.unit, "MiB"),
+
+        { /* end: all zeroes */ },
+};
+
+#define SNB_UNCORE_PCI_IMC_EVENT_MASK           0xff
+#define SNB_UNCORE_PCI_IMC_BAR_OFFSET           0x48
+
+/* page size multiple covering all config regs */
+#define SNB_UNCORE_PCI_IMC_MAP_SIZE             0x6000
+
+#define SNB_UNCORE_PCI_IMC_DATA_READS           0x1
+#define SNB_UNCORE_PCI_IMC_DATA_READS_BASE      0x5050
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES          0x2
+#define SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE     0x5054
+#define SNB_UNCORE_PCI_IMC_CTR_BASE             SNB_UNCORE_PCI_IMC_DATA_READS_BASE
+
+static struct attribute *snb_uncore_imc_formats_attr[] = {
+        &format_attr_event.attr,
+        NULL,
+};
+
+static struct attribute_group snb_uncore_imc_format_group = {
+        .name = "format",
+        .attrs = snb_uncore_imc_formats_attr,
+};
+
+static void snb_uncore_imc_init_box(struct intel_uncore_box *box)
+{
+        struct pci_dev *pdev = box->pci_dev;
+        int where = SNB_UNCORE_PCI_IMC_BAR_OFFSET;
+        resource_size_t addr;
+        u32 pci_dword;
+
+        pci_read_config_dword(pdev, where, &pci_dword);
+        addr = pci_dword;
+
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+        pci_read_config_dword(pdev, where + 4, &pci_dword);
+        addr |= ((resource_size_t)pci_dword << 32);
+#endif
+
+        addr &= ~(PAGE_SIZE - 1);
+
+        box->io_addr = ioremap(addr, SNB_UNCORE_PCI_IMC_MAP_SIZE);
+        box->hrtimer_duration = UNCORE_SNB_IMC_HRTIMER_INTERVAL;
+}
+
+static void snb_uncore_imc_enable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_disable_box(struct intel_uncore_box *box)
+{}
+
+static void snb_uncore_imc_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static void snb_uncore_imc_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{}
+
+static u64 snb_uncore_imc_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+        struct hw_perf_event *hwc = &event->hw;
+
+        return (u64)*(unsigned int *)(box->io_addr + hwc->event_base);
+}
+
+/*
+ * custom event_init() function because we define our own fixed, free
+ * running counters, so we do not want to conflict with generic uncore
+ * logic. Also simplifies processing
+ */
+static int snb_uncore_imc_event_init(struct perf_event *event)
+{
+        struct intel_uncore_pmu *pmu;
+        struct intel_uncore_box *box;
+        struct hw_perf_event *hwc = &event->hw;
+        u64 cfg = event->attr.config & SNB_UNCORE_PCI_IMC_EVENT_MASK;
+        int idx, base;
+
+        if (event->attr.type != event->pmu->type)
+                return -ENOENT;
+
+        pmu = uncore_event_to_pmu(event);
+        /* no device found for this pmu */
+        if (pmu->func_id < 0)
+                return -ENOENT;
+
+        /* Sampling not supported yet */
+        if (hwc->sample_period)
+                return -EINVAL;
+
+        /* unsupported modes and filters */
+        if (event->attr.exclude_user   ||
+            event->attr.exclude_kernel ||
+            event->attr.exclude_hv     ||
+            event->attr.exclude_idle   ||
+            event->attr.exclude_host   ||
+            event->attr.exclude_guest  ||
+            event->attr.sample_period) /* no sampling */
+                return -EINVAL;
+
+        /*
+         * Place all uncore events for a particular physical package
+         * onto a single cpu
+         */
+        if (event->cpu < 0)
+                return -EINVAL;
+
+        /* check only supported bits are set */
+        if (event->attr.config & ~SNB_UNCORE_PCI_IMC_EVENT_MASK)
+                return -EINVAL;
+
+        box = uncore_pmu_to_box(pmu, event->cpu);
+        if (!box || box->cpu < 0)
+                return -EINVAL;
+
+        event->cpu = box->cpu;
+
+        event->hw.idx = -1;
+        event->hw.last_tag = ~0ULL;
+        event->hw.extra_reg.idx = EXTRA_REG_NONE;
+        event->hw.branch_reg.idx = EXTRA_REG_NONE;
+        /*
+         * check event is known (whitelist, determines counter)
+         */
+        switch (cfg) {
+        case SNB_UNCORE_PCI_IMC_DATA_READS:
+                base = SNB_UNCORE_PCI_IMC_DATA_READS_BASE;
+                idx = UNCORE_PMC_IDX_FIXED;
+                break;
+        case SNB_UNCORE_PCI_IMC_DATA_WRITES:
+                base = SNB_UNCORE_PCI_IMC_DATA_WRITES_BASE;
+                idx = UNCORE_PMC_IDX_FIXED + 1;
+                break;
+        default:
+                return -EINVAL;
+        }
+
+        /* must be done before validate_group */
+        event->hw.event_base = base;
+        event->hw.config = cfg;
+        event->hw.idx = idx;
+
+        /* no group validation needed, we have free running counters */
+
+        return 0;
+}
+
+static int snb_uncore_imc_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+        return 0;
+}
+
+static void snb_uncore_imc_event_start(struct perf_event *event, int flags)
+{
+        struct intel_uncore_box *box = uncore_event_to_box(event);
+        u64 count;
+
+        if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED)))
+                return;
+
+        event->hw.state = 0;
+        box->n_active++;
+
+        list_add_tail(&event->active_entry, &box->active_list);
+
+        count = snb_uncore_imc_read_counter(box, event);
+        local64_set(&event->hw.prev_count, count);
+
+        if (box->n_active == 1)
+                uncore_pmu_start_hrtimer(box);
+}
+
+static void snb_uncore_imc_event_stop(struct perf_event *event, int flags)
+{
+        struct intel_uncore_box *box = uncore_event_to_box(event);
+        struct hw_perf_event *hwc = &event->hw;
+
+        if (!(hwc->state & PERF_HES_STOPPED)) {
+                box->n_active--;
+
+                WARN_ON_ONCE(hwc->state & PERF_HES_STOPPED);
+                hwc->state |= PERF_HES_STOPPED;
+
+                list_del(&event->active_entry);
+
+                if (box->n_active == 0)
+                        uncore_pmu_cancel_hrtimer(box);
+        }
+
+        if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
+                /*
+                 * Drain the remaining delta count out of a event
+                 * that we are disabling:
+                 */
+                uncore_perf_event_update(box, event);
+                hwc->state |= PERF_HES_UPTODATE;
+        }
+}
+
+static int snb_uncore_imc_event_add(struct perf_event *event, int flags)
+{
+        struct intel_uncore_box *box = uncore_event_to_box(event);
+        struct hw_perf_event *hwc = &event->hw;
+
+        if (!box)
+                return -ENODEV;
+
+        hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+        if (!(flags & PERF_EF_START))
+                hwc->state |= PERF_HES_ARCH;
+
+        snb_uncore_imc_event_start(event, 0);
+
+        box->n_events++;
+
+        return 0;
+}
+
+static void snb_uncore_imc_event_del(struct perf_event *event, int flags)
+{
+        struct intel_uncore_box *box = uncore_event_to_box(event);
+        int i;
+
+        snb_uncore_imc_event_stop(event, PERF_EF_UPDATE);
+
+        for (i = 0; i < box->n_events; i++) {
+                if (event == box->event_list[i]) {
+                        --box->n_events;
+                        break;
+                }
+        }
+}
+
+static int snb_pci2phy_map_init(int devid)
+{
+        struct pci_dev *dev = NULL;
+        int bus;
+
+        dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, dev);
+        if (!dev)
+                return -ENOTTY;
+
+        bus = dev->bus->number;
+
+        pcibus_to_physid[bus] = 0;
+
+        pci_dev_put(dev);
+
+        return 0;
+}
+
+static struct pmu snb_uncore_imc_pmu = {
+        .task_ctx_nr    = perf_invalid_context,
+        .event_init     = snb_uncore_imc_event_init,
+        .add            = snb_uncore_imc_event_add,
+        .del            = snb_uncore_imc_event_del,
+        .start          = snb_uncore_imc_event_start,
+        .stop           = snb_uncore_imc_event_stop,
+        .read           = uncore_pmu_event_read,
+};
+
+static struct intel_uncore_ops snb_uncore_imc_ops = {
+        .init_box       = snb_uncore_imc_init_box,
+        .enable_box     = snb_uncore_imc_enable_box,
+        .disable_box    = snb_uncore_imc_disable_box,
+        .disable_event  = snb_uncore_imc_disable_event,
+        .enable_event   = snb_uncore_imc_enable_event,
+        .hw_config      = snb_uncore_imc_hw_config,
+        .read_counter   = snb_uncore_imc_read_counter,
+};
+
+static struct intel_uncore_type snb_uncore_imc = {
+        .name           = "imc",
+        .num_counters   = 2,
+        .num_boxes      = 1,
+        .fixed_ctr_bits = 32,
+        .fixed_ctr      = SNB_UNCORE_PCI_IMC_CTR_BASE,
+        .event_descs    = snb_uncore_imc_events,
+        .format_group   = &snb_uncore_imc_format_group,
+        .perf_ctr       = SNB_UNCORE_PCI_IMC_DATA_READS_BASE,
+        .event_mask     = SNB_UNCORE_PCI_IMC_EVENT_MASK,
+        .ops            = &snb_uncore_imc_ops,
+        .pmu            = &snb_uncore_imc_pmu,
+};
+
+static struct intel_uncore_type *snb_pci_uncores[] = {
+        [SNB_PCI_UNCORE_IMC]    = &snb_uncore_imc,
+        NULL,
+};
+
+static DEFINE_PCI_DEVICE_TABLE(snb_uncore_pci_ids) = {
+        { /* IMC */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SNB_IMC),
+                .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+        },
+        { /* end: all zeroes */ },
+};
+
+static DEFINE_PCI_DEVICE_TABLE(ivb_uncore_pci_ids) = {
+        { /* IMC */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_IMC),
+                .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+        },
+        { /* end: all zeroes */ },
+};
+
+static DEFINE_PCI_DEVICE_TABLE(hsw_uncore_pci_ids) = {
+        { /* IMC */
+                PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_HSW_IMC),
+                .driver_data = UNCORE_PCI_DEV_DATA(SNB_PCI_UNCORE_IMC, 0),
+        },
+        { /* end: all zeroes */ },
+};
+
+static struct pci_driver snb_uncore_pci_driver = {
+        .name           = "snb_uncore",
+        .id_table       = snb_uncore_pci_ids,
+};
+
+static struct pci_driver ivb_uncore_pci_driver = {
+        .name           = "ivb_uncore",
+        .id_table       = ivb_uncore_pci_ids,
+};
+
+static struct pci_driver hsw_uncore_pci_driver = {
+        .name           = "hsw_uncore",
+        .id_table       = hsw_uncore_pci_ids,
+};
+
 /* end of Sandy Bridge uncore support */
 
 /* Nehalem uncore support */
@@ -2789,6 +3173,7 @@ again:
 static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 {
         struct intel_uncore_box *box;
+        struct perf_event *event;
         unsigned long flags;
         int bit;
 
@@ -2801,19 +3186,27 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
          */
         local_irq_save(flags);
 
+        /*
+         * handle boxes with an active event list as opposed to active
+         * counters
+         */
+        list_for_each_entry(event, &box->active_list, active_entry) {
+                uncore_perf_event_update(box, event);
+        }
+
         for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
                 uncore_perf_event_update(box, box->events[bit]);
 
         local_irq_restore(flags);
 
-        hrtimer_forward_now(hrtimer, ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL));
+        hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration));
         return HRTIMER_RESTART;
 }
 
 static void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
         __hrtimer_start_range_ns(&box->hrtimer,
-                        ns_to_ktime(UNCORE_PMU_HRTIMER_INTERVAL), 0,
+                        ns_to_ktime(box->hrtimer_duration), 0,
                         HRTIMER_MODE_REL_PINNED, 0);
 }
 
@@ -2847,43 +3240,12 @@ static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
         box->cpu = -1;
         box->phys_id = -1;
 
-        return box;
-}
-
-static struct intel_uncore_box *
-uncore_pmu_to_box(struct intel_uncore_pmu *pmu, int cpu)
-{
-        struct intel_uncore_box *box;
-
-        box = *per_cpu_ptr(pmu->box, cpu);
-        if (box)
-                return box;
-
-        raw_spin_lock(&uncore_box_lock);
-        list_for_each_entry(box, &pmu->box_list, list) {
-                if (box->phys_id == topology_physical_package_id(cpu)) {
-                        atomic_inc(&box->refcnt);
-                        *per_cpu_ptr(pmu->box, cpu) = box;
-                        break;
-                }
-        }
-        raw_spin_unlock(&uncore_box_lock);
-
-        return *per_cpu_ptr(pmu->box, cpu);
-}
+        /* set default hrtimer timeout */
+        box->hrtimer_duration = UNCORE_PMU_HRTIMER_INTERVAL;
 
-static struct intel_uncore_pmu *uncore_event_to_pmu(struct perf_event *event)
-{
-        return container_of(event->pmu, struct intel_uncore_pmu, pmu);
-}
+        INIT_LIST_HEAD(&box->active_list);
 
-static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
-{
-        /*
-         * perf core schedules event on the basis of cpu, uncore events are
-         * collected by one of the cpus inside a physical package.
-         */
-        return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
+        return box;
 }
 
 static int
@@ -3279,16 +3641,21 @@ static int __init uncore_pmu_register(struct intel_uncore_pmu *pmu)
 {
         int ret;
 
-        pmu->pmu = (struct pmu) {
-                .attr_groups    = pmu->type->attr_groups,
-                .task_ctx_nr    = perf_invalid_context,
-                .event_init     = uncore_pmu_event_init,
-                .add            = uncore_pmu_event_add,
-                .del            = uncore_pmu_event_del,
-                .start          = uncore_pmu_event_start,
-                .stop           = uncore_pmu_event_stop,
-                .read           = uncore_pmu_event_read,
-        };
+        if (!pmu->type->pmu) {
+                pmu->pmu = (struct pmu) {
+                        .attr_groups    = pmu->type->attr_groups,
+                        .task_ctx_nr    = perf_invalid_context,
+                        .event_init     = uncore_pmu_event_init,
+                        .add            = uncore_pmu_event_add,
+                        .del            = uncore_pmu_event_del,
+                        .start          = uncore_pmu_event_start,
+                        .stop           = uncore_pmu_event_stop,
+                        .read           = uncore_pmu_event_read,
+                };
+        } else {
+                pmu->pmu = *pmu->type->pmu;
+                pmu->pmu.attr_groups = pmu->type->attr_groups;
+        }
 
         if (pmu->type->num_boxes == 1) {
                 if (strlen(pmu->type->name) > 0)
@@ -3334,6 +3701,8 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
         if (!pmus)
                 return -ENOMEM;
 
+        type->pmus = pmus;
+
         type->unconstrainted = (struct event_constraint)
                 __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1,
                                 0, type->num_counters, 0, 0);
@@ -3369,7 +3738,6 @@ static int __init uncore_type_init(struct intel_uncore_type *type)
         }
 
         type->pmu_group = &uncore_pmu_attr_group;
-        type->pmus = pmus;
         return 0;
 fail:
         uncore_type_exit(type);
@@ -3501,6 +3869,28 @@ static int __init uncore_pci_init(void)
                 pci_uncores = ivt_pci_uncores;
                 uncore_pci_driver = &ivt_uncore_pci_driver;
                 break;
+        case 42: /* Sandy Bridge */
+                ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_SNB_IMC);
+                if (ret)
+                        return ret;
+                pci_uncores = snb_pci_uncores;
+                uncore_pci_driver = &snb_uncore_pci_driver;
+                break;
+        case 58: /* Ivy Bridge */
+                ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_IVB_IMC);
+                if (ret)
+                        return ret;
+                pci_uncores = snb_pci_uncores;
+                uncore_pci_driver = &ivb_uncore_pci_driver;
+                break;
+        case 60: /* Haswell */
+        case 69: /* Haswell Celeron */
+                ret = snb_pci2phy_map_init(PCI_DEVICE_ID_INTEL_HSW_IMC);
+                if (ret)
+                        return ret;
+                pci_uncores = snb_pci_uncores;
+                uncore_pci_driver = &hsw_uncore_pci_driver;
+                break;
         default:
                 return 0;
         }
@@ -3772,7 +4162,7 @@ static void __init uncore_cpu_setup(void *dummy)
 
 static int __init uncore_cpu_init(void)
 {
-        int ret, cpu, max_cores;
+        int ret, max_cores;
 
         max_cores = boot_cpu_data.x86_max_cores;
         switch (boot_cpu_data.x86_model) {
@@ -3816,29 +4206,6 @@ static int __init uncore_cpu_init(void)
         if (ret)
                 return ret;
 
-        get_online_cpus();
-
-        for_each_online_cpu(cpu) {
-                int i, phys_id = topology_physical_package_id(cpu);
-
-                for_each_cpu(i, &uncore_cpu_mask) {
-                        if (phys_id == topology_physical_package_id(i)) {
-                                phys_id = -1;
-                                break;
-                        }
-                }
-                if (phys_id < 0)
-                        continue;
-
-                uncore_cpu_prepare(cpu, phys_id);
-                uncore_event_init_cpu(cpu);
-        }
-        on_each_cpu(uncore_cpu_setup, NULL, 1);
-
-        register_cpu_notifier(&uncore_cpu_nb);
-
-        put_online_cpus();
-
         return 0;
 }
 
@@ -3867,6 +4234,41 @@ static int __init uncore_pmus_register(void)
         return 0;
 }
 
+static void __init uncore_cpumask_init(void)
+{
+        int cpu;
+
+        /*
+         * ony invoke once from msr or pci init code
+         */
+        if (!cpumask_empty(&uncore_cpu_mask))
+                return;
+
+        get_online_cpus();
+
+        for_each_online_cpu(cpu) {
+                int i, phys_id = topology_physical_package_id(cpu);
+
+                for_each_cpu(i, &uncore_cpu_mask) {
+                        if (phys_id == topology_physical_package_id(i)) {
+                                phys_id = -1;
+                                break;
+                        }
+                }
+                if (phys_id < 0)
+                        continue;
+
+                uncore_cpu_prepare(cpu, phys_id);
+                uncore_event_init_cpu(cpu);
+        }
+        on_each_cpu(uncore_cpu_setup, NULL, 1);
+
+        register_cpu_notifier(&uncore_cpu_nb);
+
+        put_online_cpus();
+}
+
+
 static int __init intel_uncore_init(void)
 {
         int ret;
@@ -3885,6 +4287,7 @@ static int __init intel_uncore_init(void)
                 uncore_pci_exit();
                 goto fail;
         }
+        uncore_cpumask_init();
 
         uncore_pmus_register();
         return 0;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index a80ab71a883d..90236f0c94a9 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -6,6 +6,7 @@
 
 #define UNCORE_PMU_NAME_LEN             32
 #define UNCORE_PMU_HRTIMER_INTERVAL     (60LL * NSEC_PER_SEC)
+#define UNCORE_SNB_IMC_HRTIMER_INTERVAL (5ULL * NSEC_PER_SEC)
 
 #define UNCORE_FIXED_EVENT              0xff
 #define UNCORE_PMC_IDX_MAX_GENERIC      8
@@ -440,6 +441,7 @@ struct intel_uncore_type {
         struct intel_uncore_ops *ops;
         struct uncore_event_desc *event_descs;
         const struct attribute_group *attr_groups[4];
+        struct pmu *pmu; /* for custom pmu ops */
 };
 
 #define pmu_group attr_groups[0]
@@ -488,8 +490,11 @@ struct intel_uncore_box {
         u64 tags[UNCORE_PMC_IDX_MAX];
         struct pci_dev *pci_dev;
         struct intel_uncore_pmu *pmu;
+        u64 hrtimer_duration; /* hrtimer timeout for this box */
         struct hrtimer hrtimer;
         struct list_head list;
+        struct list_head active_list;
+        void *io_addr;
         struct intel_uncore_extra_reg shared_regs[0];
 };
 
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 3486e6660357..5d466b7d8609 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1257,7 +1257,24 @@ again:
                         pass++;
                         goto again;
                 }
-
+                /*
+                 * Perf does test runs to see if a whole group can be assigned
+                 * together succesfully.  There can be multiple rounds of this.
+                 * Unfortunately, p4_pmu_swap_config_ts touches the hwc->config
+                 * bits, such that the next round of group assignments will
+                 * cause the above p4_should_swap_ts to pass instead of fail.
+                 * This leads to counters exclusive to thread0 being used by
+                 * thread1.
+                 *
+                 * Solve this with a cheap hack, reset the idx back to -1 to
+                 * force a new lookup (p4_next_cntr) to get the right counter
+                 * for the right thread.
+                 *
+                 * This probably doesn't comply with the general spirit of how
+                 * perf wants to work, but P4 is special. :-(
+                 */
+                if (p4_should_swap_ts(hwc->config, cpu))
+                        hwc->idx = -1;
                 p4_pmu_swap_config_ts(hwc, cpu);
                 if (assign)
                         assign[i] = cntr_idx;
@@ -1322,6 +1339,7 @@ static __initconst const struct x86_pmu p4_pmu = {
 __init int p4_pmu_init(void)
 {
         unsigned int low, high;
+        int i, reg;
 
         /* If we get stripped -- indexing fails */
         BUILD_BUG_ON(ARCH_P4_MAX_CCCR > INTEL_PMC_MAX_GENERIC);
@@ -1340,5 +1358,19 @@ __init int p4_pmu_init(void)
 
         x86_pmu = p4_pmu;
 
+        /*
+         * Even though the counters are configured to interrupt a particular
+         * logical processor when an overflow happens, testing has shown that
+         * on kdump kernels (which uses a single cpu), thread1's counter
+         * continues to run and will report an NMI on thread0.  Due to the
+         * overflow bug, this leads to a stream of unknown NMIs.
+         *
+         * Solve this by zero'ing out the registers to mimic a reset.
+         */
+        for (i = 0; i < x86_pmu.num_counters; i++) {
+                reg = x86_pmu_config_addr(i);
+                wrmsrl_safe(reg, 0ULL);
+        }
+
         return 0;
 }
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index a57902efe2d5..507de8066594 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -57,9 +57,7 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 {
 #ifdef CONFIG_X86_32
         struct pt_regs fixed_regs;
-#endif
 
-#ifdef CONFIG_X86_32
         if (!user_mode_vm(regs)) {
                 crash_fixup_ss_esp(&fixed_regs, regs);
                 regs = &fixed_regs;
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index f2a1770ca176..5abd4cd4230c 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -16,12 +16,35 @@
 
 #include <asm/stacktrace.h>
 
+static void *is_irq_stack(void *p, void *irq)
+{
+        if (p < irq || p >= (irq + THREAD_SIZE))
+                return NULL;
+        return irq + THREAD_SIZE;
+}
+
+
+static void *is_hardirq_stack(unsigned long *stack, int cpu)
+{
+        void *irq = per_cpu(hardirq_stack, cpu);
+
+        return is_irq_stack(stack, irq);
+}
+
+static void *is_softirq_stack(unsigned long *stack, int cpu)
+{
+        void *irq = per_cpu(softirq_stack, cpu);
+
+        return is_irq_stack(stack, irq);
+}
 
 void dump_trace(struct task_struct *task, struct pt_regs *regs,
                 unsigned long *stack, unsigned long bp,
                 const struct stacktrace_ops *ops, void *data)
 {
+        const unsigned cpu = get_cpu();
         int graph = 0;
+        u32 *prev_esp;
 
         if (!task)
                 task = current;
@@ -30,7 +53,7 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                 unsigned long dummy;
 
                 stack = &dummy;
-                if (task && task != current)
+                if (task != current)
                         stack = (unsigned long *)task->thread.sp;
         }
 
@@ -39,18 +62,31 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
 
         for (;;) {
                 struct thread_info *context;
+                void *end_stack;
+
+                end_stack = is_hardirq_stack(stack, cpu);
+                if (!end_stack)
+                        end_stack = is_softirq_stack(stack, cpu);
 
-                context = (struct thread_info *)
-                        ((unsigned long)stack & (~(THREAD_SIZE - 1)));
-                bp = ops->walk_stack(context, stack, bp, ops, data, NULL, &graph);
+                context = task_thread_info(task);
+                bp = ops->walk_stack(context, stack, bp, ops, data,
+                                     end_stack, &graph);
 
-                stack = (unsigned long *)context->previous_esp;
+                /* Stop if not on irq stack */
+                if (!end_stack)
+                        break;
+
+                /* The previous esp is saved on the bottom of the stack */
+                prev_esp = (u32 *)(end_stack - THREAD_SIZE);
+                stack = (unsigned long *)*prev_esp;
                 if (!stack)
                         break;
+
                 if (ops->stack(data, "IRQ") < 0)
                         break;
                 touch_nmi_watchdog();
         }
+        put_cpu();
 }
 EXPORT_SYMBOL(dump_trace);
 
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index addb207dab92..346b1df2412e 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -104,6 +104,45 @@ in_irq_stack(unsigned long *stack, unsigned long *irq_stack,
         return (stack >= irq_stack && stack < irq_stack_end);
 }
 
+static const unsigned long irq_stack_size =
+        (IRQ_STACK_SIZE - 64) / sizeof(unsigned long);
+
+enum stack_type {
+        STACK_IS_UNKNOWN,
+        STACK_IS_NORMAL,
+        STACK_IS_EXCEPTION,
+        STACK_IS_IRQ,
+};
+
+static enum stack_type
+analyze_stack(int cpu, struct task_struct *task,
+              unsigned long *stack, unsigned long **stack_end, char **id)
+{
+        unsigned long *irq_stack;
+        unsigned long addr;
+        unsigned used = 0;
+
+        addr = ((unsigned long)stack & (~(THREAD_SIZE - 1)));
+        if ((unsigned long)task_stack_page(task) == addr)
+                return STACK_IS_NORMAL;
+
+        *stack_end = in_exception_stack(cpu, (unsigned long)stack,
+                                         &used, id);
+        if (*stack_end)
+                return STACK_IS_EXCEPTION;
+
+        *stack_end = (unsigned long *)per_cpu(irq_stack_ptr, cpu);
+        if (!*stack_end)
+                return STACK_IS_UNKNOWN;
+
+        irq_stack = *stack_end - irq_stack_size;
+
+        if (in_irq_stack(stack, irq_stack, *stack_end))
+                return STACK_IS_IRQ;
+
+        return STACK_IS_UNKNOWN;
+}
+
 /*
  * x86-64 can have up to three kernel stacks:
  * process stack
@@ -116,12 +155,11 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
                 const struct stacktrace_ops *ops, void *data)
 {
         const unsigned cpu = get_cpu();
-        unsigned long *irq_stack_end =
-                (unsigned long *)per_cpu(irq_stack_ptr, cpu);
-        unsigned used = 0;
         struct thread_info *tinfo;
-        int graph = 0;
+        unsigned long *irq_stack;
         unsigned long dummy;
+        int graph = 0;
+        int done = 0;
 
         if (!task)
                 task = current;
@@ -143,49 +181,60 @@ void dump_trace(struct task_struct *task, struct pt_regs *regs,
          * exceptions
          */
         tinfo = task_thread_info(task);
-        for (;;) {
+        while (!done) {
+                unsigned long *stack_end;
+                enum stack_type stype;
                 char *id;
-                unsigned long *estack_end;
-                estack_end = in_exception_stack(cpu, (unsigned long)stack,
-                                                &used, &id);
 
-                if (estack_end) {
+                stype = analyze_stack(cpu, task, stack, &stack_end, &id);
+
+                /* Default finish unless specified to continue */
+                done = 1;
+
+                switch (stype) {
+
+                /* Break out early if we are on the thread stack */
+                case STACK_IS_NORMAL:
+                        break;
+
+                case STACK_IS_EXCEPTION:
+
                         if (ops->stack(data, id) < 0)
                                 break;
 
                         bp = ops->walk_stack(tinfo, stack, bp, ops,
-                                             data, estack_end, &graph);
+                                             data, stack_end, &graph);
                         ops->stack(data, "<EOE>");
                         /*
                          * We link to the next stack via the
                          * second-to-last pointer (index -2 to end) in the
                          * exception stack:
                          */
-                        stack = (unsigned long *) estack_end[-2];
-                        continue;
-                }
-                if (irq_stack_end) {
-                        unsigned long *irq_stack;
-                        irq_stack = irq_stack_end -
-                                (IRQ_STACK_SIZE - 64) / sizeof(*irq_stack);
-
-                        if (in_irq_stack(stack, irq_stack, irq_stack_end)) {
-                                if (ops->stack(data, "IRQ") < 0)
-                                        break;
-                                bp = ops->walk_stack(tinfo, stack, bp,
-                                        ops, data, irq_stack_end, &graph);
-                                /*
-                                 * We link to the next stack (which would be
-                                 * the process stack normally) the last
-                                 * pointer (index -1 to end) in the IRQ stack:
-                                 */
-                                stack = (unsigned long *) (irq_stack_end[-1]);
-                                irq_stack_end = NULL;
-                                ops->stack(data, "EOI");
-                                continue;
-                        }
+                        stack = (unsigned long *) stack_end[-2];
+                        done = 0;
+                        break;
+
+                case STACK_IS_IRQ:
+
+                        if (ops->stack(data, "IRQ") < 0)
+                                break;
+                        bp = ops->walk_stack(tinfo, stack, bp,
+                                     ops, data, stack_end, &graph);
+                        /*
+                         * We link to the next stack (which would be
+                         * the process stack normally) the last
+                         * pointer (index -1 to end) in the IRQ stack:
+                         */
+                        stack = (unsigned long *) (stack_end[-1]);
+                        irq_stack = stack_end - irq_stack_size;
+                        ops->stack(data, "EOI");
+                        done = 0;
+                        break;
+
+                case STACK_IS_UNKNOWN:
+                        ops->stack(data, "UNK");
+                        break;
                 }
-                break;
         }
 
         /*
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bc4a088f9023..6d7d5a1260a6 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -203,18 +203,15 @@ static void __init intel_remapping_check(int num, int slot, int func)
         revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
 
         /*
-         * Revision 13 of all triggering devices id in this quirk have
-         * a problem draining interrupts when irq remapping is enabled,
-         * and should be flagged as broken.  Additionally revisions 0x12
-         * and 0x22 of device id 0x3405 has this problem.
+         * Revision <= 13 of all triggering devices id in this quirk
+         * have a problem draining interrupts when irq remapping is
+         * enabled, and should be flagged as broken. Additionally
+         * revision 0x22 of device id 0x3405 has this problem.
          */
-        if (revision == 0x13)
+        if (revision <= 0x13)
                 set_irq_remapping_broken();
-        else if ((device == 0x3405) &&
-            ((revision == 0x12) ||
-             (revision == 0x22)))
+        else if (device == 0x3405 && revision == 0x22)
                 set_irq_remapping_broken();
-
 }
 
 /*
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 81ba27679f18..f36bd42d6f0c 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -544,6 +544,10 @@ ENDPROC(early_idt_handlers)
         /* This is global to keep gas from relaxing the jumps */
 ENTRY(early_idt_handler)
         cld
+
+        cmpl $2,(%esp)          # X86_TRAP_NMI
+        je is_nmi               # Ignore NMI
+
         cmpl $2,%ss:early_recursion_flag
         je hlt_loop
         incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@ ex_entry:
         pop %edx
         pop %ecx
         pop %eax
-        addl $8,%esp            /* drop vector number and error code */
         decl %ss:early_recursion_flag
+is_nmi:
+        addl $8,%esp            /* drop vector number and error code */
         iret
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e1aabdb314c8..a468c0a65c42 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -343,6 +343,9 @@ early_idt_handlers:
 ENTRY(early_idt_handler)
         cld
 
+        cmpl $2,(%rsp)          # X86_TRAP_NMI
+        je is_nmi               # Ignore NMI
+
         cmpl $2,early_recursion_flag(%rip)
         jz  1f
         incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@ ENTRY(early_idt_handler)
         popq %rdx
         popq %rcx
         popq %rax
-        addq $16,%rsp           # drop vector number and error code
         decl early_recursion_flag(%rip)
+is_nmi:
+        addq $16,%rsp           # drop vector number and error code
         INTERRUPT_RETURN
 ENDPROC(early_idt_handler)
 
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index da85a8e830a1..014618dbaa7b 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -521,7 +521,7 @@ static int hpet_setup_irq(struct hpet_dev *dev)
 {
 
         if (request_irq(dev->irq, hpet_interrupt_handler,
-                        IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
+                        IRQF_TIMER | IRQF_NOBALANCING,
                         dev->name, dev))
                 return -1;
 
@@ -699,7 +699,7 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
                 /* FIXME: add schedule_work_on() */
                 schedule_delayed_work_on(cpu, &work.work, 0);
                 wait_for_completion(&work.complete);
-                destroy_timer_on_stack(&work.work.timer);
+                destroy_delayed_work_on_stack(&work.work);
                 break;
         case CPU_DEAD:
                 if (hdev) {
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index e8368c6dd2a2..d5dd80814419 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -86,10 +86,19 @@ EXPORT_SYMBOL(__kernel_fpu_begin);
 
 void __kernel_fpu_end(void)
 {
-        if (use_eager_fpu())
-                math_state_restore();
-        else
+        if (use_eager_fpu()) {
+                /*
+                 * For eager fpu, most the time, tsk_used_math() is true.
+                 * Restore the user math as we are done with the kernel usage.
+                 * At few instances during thread exit, signal handling etc,
+                 * tsk_used_math() is false. Those few places will take proper
+                 * actions, so we don't need to restore the math here.
+                 */
+                if (likely(tsk_used_math(current)))
+                        math_state_restore();
+        } else {
                 stts();
+        }
 }
 EXPORT_SYMBOL(__kernel_fpu_end);
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index d99f31d9a750..42805fac0092 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -125,6 +125,12 @@ int arch_show_interrupts(struct seq_file *p, int prec)
                 seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
         seq_printf(p, "  Machine check polls\n");
 #endif
+#if defined(CONFIG_HYPERV) || defined(CONFIG_XEN)
+        seq_printf(p, "%*s: ", prec, "THR");
+        for_each_online_cpu(j)
+                seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
+        seq_printf(p, "  Hypervisor callback interrupts\n");
+#endif
         seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
         seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index d7fcbedc9c43..63ce838e5a54 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -55,16 +55,8 @@ static inline int check_stack_overflow(void) { return 0; }
 static inline void print_stack_overflow(void) { }
 #endif
 
-/*
- * per-CPU IRQ handling contexts (thread information and stack)
- */
-union irq_ctx {
-        struct thread_info      tinfo;
-        u32                     stack[THREAD_SIZE/sizeof(u32)];
-} __attribute__((aligned(THREAD_SIZE)));
-
-static DEFINE_PER_CPU(union irq_ctx *, hardirq_ctx);
-static DEFINE_PER_CPU(union irq_ctx *, softirq_ctx);
+DEFINE_PER_CPU(struct irq_stack *, hardirq_stack);
+DEFINE_PER_CPU(struct irq_stack *, softirq_stack);
 
 static void call_on_stack(void *func, void *stack)
 {
@@ -77,14 +69,26 @@ static void call_on_stack(void *func, void *stack)
                      : "memory", "cc", "edx", "ecx", "eax");
 }
 
+/* how to get the current stack pointer from C */
+#define current_stack_pointer ({                \
+        unsigned long sp;                       \
+        asm("mov %%esp,%0" : "=g" (sp));        \
+        sp;                                     \
+})
+
+static inline void *current_stack(void)
+{
+        return (void *)(current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
 static inline int
 execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
 {
-        union irq_ctx *curctx, *irqctx;
-        u32 *isp, arg1, arg2;
+        struct irq_stack *curstk, *irqstk;
+        u32 *isp, *prev_esp, arg1, arg2;
 
-        curctx = (union irq_ctx *) current_thread_info();
-        irqctx = __this_cpu_read(hardirq_ctx);
+        curstk = (struct irq_stack *) current_stack();
+        irqstk = __this_cpu_read(hardirq_stack);
 
         /*
          * this is where we switch to the IRQ stack. However, if we are
@@ -92,13 +96,14 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
          * handler) we can't do that and just have to keep using the
          * current stack (which is the irq stack already after all)
          */
-        if (unlikely(curctx == irqctx))
+        if (unlikely(curstk == irqstk))
                 return 0;
 
-        /* build the stack frame on the IRQ stack */
-        isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
-        irqctx->tinfo.task = curctx->tinfo.task;
-        irqctx->tinfo.previous_esp = current_stack_pointer;
+        isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
+
+        /* Save the next esp at the bottom of the stack */
+        prev_esp = (u32 *)irqstk;
+        *prev_esp = current_stack_pointer;
 
         if (unlikely(overflow))
                 call_on_stack(print_stack_overflow, isp);
@@ -118,46 +123,40 @@ execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
  */
 void irq_ctx_init(int cpu)
 {
-        union irq_ctx *irqctx;
+        struct irq_stack *irqstk;
 
-        if (per_cpu(hardirq_ctx, cpu))
+        if (per_cpu(hardirq_stack, cpu))
                 return;
 
-        irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+        irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
                                                THREADINFO_GFP,
                                                THREAD_SIZE_ORDER));
-        memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
-        irqctx->tinfo.cpu               = cpu;
-        irqctx->tinfo.addr_limit        = MAKE_MM_SEG(0);
-
-        per_cpu(hardirq_ctx, cpu) = irqctx;
+        per_cpu(hardirq_stack, cpu) = irqstk;
 
-        irqctx = page_address(alloc_pages_node(cpu_to_node(cpu),
+        irqstk = page_address(alloc_pages_node(cpu_to_node(cpu),
                                                THREADINFO_GFP,
                                                THREAD_SIZE_ORDER));
-        memset(&irqctx->tinfo, 0, sizeof(struct thread_info));
-        irqctx->tinfo.cpu               = cpu;
-        irqctx->tinfo.addr_limit        = MAKE_MM_SEG(0);
-
-        per_cpu(softirq_ctx, cpu) = irqctx;
+        per_cpu(softirq_stack, cpu) = irqstk;
 
         printk(KERN_DEBUG "CPU %u irqstacks, hard=%p soft=%p\n",
-               cpu, per_cpu(hardirq_ctx, cpu),  per_cpu(softirq_ctx, cpu));
+               cpu, per_cpu(hardirq_stack, cpu),  per_cpu(softirq_stack, cpu));
 }
 
 void do_softirq_own_stack(void)
 {
-        struct thread_info *curctx;
-        union irq_ctx *irqctx;
-        u32 *isp;
+        struct thread_info *curstk;
+        struct irq_stack *irqstk;
+        u32 *isp, *prev_esp;
 
-        curctx = current_thread_info();
-        irqctx = __this_cpu_read(softirq_ctx);
-        irqctx->tinfo.task = curctx->task;
-        irqctx->tinfo.previous_esp = current_stack_pointer;
+        curstk = current_stack();
+        irqstk = __this_cpu_read(softirq_stack);
 
         /* build the stack frame on the softirq stack */
-        isp = (u32 *) ((char *)irqctx + sizeof(*irqctx));
+        isp = (u32 *) ((char *)irqstk + sizeof(*irqstk));
+
+        /* Push the previous esp onto the stack */
+        prev_esp = (u32 *)irqstk;
+        *prev_esp = current_stack_pointer;
 
         call_on_stack(__do_softirq, isp);
 }
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 4eabc160696f..679cef0791cd 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -279,5 +279,7 @@ void arch_crash_save_vmcoreinfo(void)
         VMCOREINFO_SYMBOL(node_data);
         VMCOREINFO_LENGTH(node_data, MAX_NUMNODES);
 #endif
+        vmcoreinfo_append_str("KERNELOFFSET=%lx\n",
+                              (unsigned long)&_text - __START_KERNEL);
 }
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 18be189368bb..e69f9882bf95 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -28,6 +28,7 @@
 #include <linux/mm.h>
 #include <linux/gfp.h>
 #include <linux/jump_label.h>
+#include <linux/random.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -43,13 +44,52 @@ do {							\
 } while (0)
 #endif
 
+#ifdef CONFIG_RANDOMIZE_BASE
+static unsigned long module_load_offset;
+static int randomize_modules = 1;
+
+/* Mutex protects the module_load_offset. */
+static DEFINE_MUTEX(module_kaslr_mutex);
+
+static int __init parse_nokaslr(char *p)
+{
+        randomize_modules = 0;
+        return 0;
+}
+early_param("nokaslr", parse_nokaslr);
+
+static unsigned long int get_module_load_offset(void)
+{
+        if (randomize_modules) {
+                mutex_lock(&module_kaslr_mutex);
+                /*
+                 * Calculate the module_load_offset the first time this
+                 * code is called. Once calculated it stays the same until
+                 * reboot.
+                 */
+                if (module_load_offset == 0)
+                        module_load_offset =
+                                (get_random_int() % 1024 + 1) * PAGE_SIZE;
+                mutex_unlock(&module_kaslr_mutex);
+        }
+        return module_load_offset;
+}
+#else
+static unsigned long int get_module_load_offset(void)
+{
+        return 0;
+}
+#endif
+
 void *module_alloc(unsigned long size)
 {
         if (PAGE_ALIGN(size) > MODULES_LEN)
                 return NULL;
-        return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END,
-                                GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
-                                NUMA_NO_NODE, __builtin_return_address(0));
+        return __vmalloc_node_range(size, 1,
+                                    MODULES_VADDR + get_module_load_offset(),
+                                    MODULES_END, GFP_KERNEL | __GFP_HIGHMEM,
+                                    PAGE_KERNEL_EXEC, NUMA_NO_NODE,
+                                    __builtin_return_address(0));
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 6fcb49ce50a1..b4872b999a71 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -87,6 +87,7 @@ __setup("unknown_nmi_panic", setup_unknown_nmi_panic);
 #define nmi_to_desc(type) (&nmi_desc[type])
 
 static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;
+
 static int __init nmi_warning_debugfs(void)
 {
         debugfs_create_u64("nmi_longest_ns", 0644,
@@ -95,6 +96,20 @@ static int __init nmi_warning_debugfs(void)
 }
 fs_initcall(nmi_warning_debugfs);
 
+static void nmi_max_handler(struct irq_work *w)
+{
+        struct nmiaction *a = container_of(w, struct nmiaction, irq_work);
+        int remainder_ns, decimal_msecs;
+        u64 whole_msecs = ACCESS_ONCE(a->max_duration);
+
+        remainder_ns = do_div(whole_msecs, (1000 * 1000));
+        decimal_msecs = remainder_ns / 1000;
+
+        printk_ratelimited(KERN_INFO
+                "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
+                a->handler, whole_msecs, decimal_msecs);
+}
+
 static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2b)
 {
         struct nmi_desc *desc = nmi_to_desc(type);
@@ -110,26 +125,20 @@ static int __kprobes nmi_handle(unsigned int type, struct pt_regs *regs, bool b2
          * to handle those situations.
          */
         list_for_each_entry_rcu(a, &desc->head, list) {
-                u64 before, delta, whole_msecs;
-                int remainder_ns, decimal_msecs, thishandled;
+                int thishandled;
+                u64 delta;
 
-                before = sched_clock();
+                delta = sched_clock();
                 thishandled = a->handler(type, regs);
                 handled += thishandled;
-                delta = sched_clock() - before;
+                delta = sched_clock() - delta;
                 trace_nmi_handler(a->handler, (int)delta, thishandled);
 
-                if (delta < nmi_longest_ns)
+                if (delta < nmi_longest_ns || delta < a->max_duration)
                         continue;
 
-                nmi_longest_ns = delta;
-                whole_msecs = delta;
-                remainder_ns = do_div(whole_msecs, (1000 * 1000));
-                decimal_msecs = remainder_ns / 1000;
-                printk_ratelimited(KERN_INFO
-                        "INFO: NMI handler (%ps) took too long to run: "
-                        "%lld.%03d msecs\n", a->handler, whole_msecs,
-                        decimal_msecs);
+                a->max_duration = delta;
+                irq_work_queue(&a->irq_work);
         }
 
         rcu_read_unlock();
@@ -146,6 +155,8 @@ int __register_nmi_handler(unsigned int type, struct nmiaction *action)
         if (!action->handler)
                 return -EINVAL;
 
+        init_irq_work(&action->irq_work, nmi_max_handler);
+
         spin_lock_irqsave(&desc->lock, flags);
 
         /*
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 3fb8d95ab8b5..4505e2a950d8 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -298,10 +298,7 @@ void arch_cpu_idle_dead(void)
  */
 void arch_cpu_idle(void)
 {
-        if (cpuidle_idle_call())
-                x86_idle();
-        else
-                local_irq_enable();
+        x86_idle();
 }
 
 /*
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0de43e98ce08..7bc86bbe7485 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -314,6 +314,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
          */
         arch_end_context_switch(next_p);
 
+        this_cpu_write(kernel_stack,
+                  (unsigned long)task_stack_page(next_p) +
+                  THREAD_SIZE - KERNEL_STACK_OFFSET);
+
         /*
          * Restore %gs if needed (which is common)
          */
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 7461f50d5bb1..678c0ada3b3c 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -184,14 +184,14 @@ unsigned long kernel_stack_pointer(struct pt_regs *regs)
 {
         unsigned long context = (unsigned long)regs & ~(THREAD_SIZE - 1);
         unsigned long sp = (unsigned long)&regs->sp;
-        struct thread_info *tinfo;
+        u32 *prev_esp;
 
         if (context == (sp & ~(THREAD_SIZE - 1)))
                 return sp;
 
-        tinfo = (struct thread_info *)context;
-        if (tinfo->previous_esp)
-                return tinfo->previous_esp;
+        prev_esp = (u32 *)(context);
+        if (prev_esp)
+                return (unsigned long)prev_esp;
 
         return (unsigned long)regs;
 }
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 7c6acd4b8995..ff898bbf579d 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -529,7 +529,7 @@ static void quirk_amd_nb_node(struct pci_dev *dev)
                 return;
 
         pci_read_config_dword(nb_ht, 0x60, &val);
-        node = val & 7;
+        node = pcibus_to_node(dev->bus) | (val & 7);
         /*
          * Some hardware may return an invalid node ID,
          * so check it first:
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index c752cb43e52f..654b46574b91 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -464,9 +464,12 @@ void __attribute__((weak)) mach_reboot_fixups(void)
  * 2) If still alive, write to the keyboard controller
  * 3) If still alive, write to the ACPI reboot register again
  * 4) If still alive, write to the keyboard controller again
+ * 5) If still alive, call the EFI runtime service to reboot
+ * 6) If still alive, write to the PCI IO port 0xCF9 to reboot
+ * 7) If still alive, inform BIOS to do a proper reboot
  *
  * If the machine is still alive at this stage, it gives up. We default to
- * following the same pattern, except that if we're still alive after (4) we'll
+ * following the same pattern, except that if we're still alive after (7) we'll
  * try to force a triple fault and then cycle between hitting the keyboard
  * controller and doing that
  */
@@ -502,7 +505,7 @@ static void native_machine_emergency_restart(void)
                                 attempt = 1;
                                 reboot_type = BOOT_ACPI;
                         } else {
-                                reboot_type = BOOT_TRIPLE;
+                                reboot_type = BOOT_EFI;
                         }
                         break;
 
@@ -510,13 +513,15 @@ static void native_machine_emergency_restart(void)
                         load_idt(&no_idt);
                         __asm__ __volatile__("int3");
 
+                        /* We're probably dead after this, but... */
                         reboot_type = BOOT_KBD;
                         break;
 
                 case BOOT_BIOS:
                         machine_real_restart(MRR_BIOS);
 
-                        reboot_type = BOOT_KBD;
+                        /* We're probably dead after this, but... */
+                        reboot_type = BOOT_TRIPLE;
                         break;
 
                 case BOOT_ACPI:
@@ -530,7 +535,7 @@ static void native_machine_emergency_restart(void)
                                                  EFI_RESET_WARM :
                                                  EFI_RESET_COLD,
                                                  EFI_SUCCESS, 0, NULL);
-                        reboot_type = BOOT_KBD;
+                        reboot_type = BOOT_CF9_COND;
                         break;
 
                 case BOOT_CF9:
@@ -548,7 +553,7 @@ static void native_machine_emergency_restart(void)
                                 outb(cf9|reboot_code, 0xcf9);
                                 udelay(50);
                         }
-                        reboot_type = BOOT_KBD;
+                        reboot_type = BOOT_BIOS;
                         break;
                 }
         }
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 06853e670354..fa511acff7e6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -926,11 +926,11 @@ void __init setup_arch(char **cmdline_p)
 #ifdef CONFIG_EFI
         if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
                      "EL32", 4)) {
-                set_bit(EFI_BOOT, &x86_efi_facility);
+                set_bit(EFI_BOOT, &efi.flags);
         } else if (!strncmp((char *)&boot_params.efi_info.efi_loader_signature,
                      "EL64", 4)) {
-                set_bit(EFI_BOOT, &x86_efi_facility);
-                set_bit(EFI_64BIT, &x86_efi_facility);
+                set_bit(EFI_BOOT, &efi.flags);
+                set_bit(EFI_64BIT, &efi.flags);
         }
 
         if (efi_enabled(EFI_BOOT))
@@ -1239,14 +1239,8 @@ void __init setup_arch(char **cmdline_p)
         register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-        /* Once setup is done above, unmap the EFI memory map on
-         * mismatched firmware/kernel archtectures since there is no
-         * support for runtime services.
-         */
-        if (efi_enabled(EFI_BOOT) && !efi_is_native()) {
-                pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
-                efi_unmap_memmap();
-        }
+        if (efi_enabled(EFI_BOOT))
+                efi_apply_memmap_quirks();
 #endif
 }
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index a32da804252e..34826934d4a7 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -122,8 +122,9 @@ static void smp_callin(void)
          * Since CPU0 is not wakened up by INIT, it doesn't wait for the IPI.
          */
         cpuid = smp_processor_id();
-        if (apic->wait_for_init_deassert && cpuid != 0)
-                apic->wait_for_init_deassert(&init_deasserted);
+        if (apic->wait_for_init_deassert && cpuid)
+                while (!atomic_read(&init_deasserted))
+                        cpu_relax();
 
         /*
          * (This works even if the APIC is not enabled.)
@@ -701,11 +702,15 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid,
         int id;
         int boot_error;
 
+        preempt_disable();
+
         /*
          * Wake up AP by INIT, INIT, STARTUP sequence.
          */
-        if (cpu)
-                return wakeup_secondary_cpu_via_init(apicid, start_ip);
+        if (cpu) {
+                boot_error = wakeup_secondary_cpu_via_init(apicid, start_ip);
+                goto out;
+        }
 
         /*
          * Wake up BSP by nmi.
@@ -725,6 +730,9 @@ wakeup_cpu_via_init_nmi(int cpu, unsigned long start_ip, int apicid,
                 boot_error = wakeup_secondary_cpu_via_nmi(id, start_ip);
         }
 
+out:
+        preempt_enable();
+
         return boot_error;
 }
 
@@ -758,10 +766,10 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
 #else
         clear_tsk_thread_flag(idle, TIF_FORK);
         initial_gs = per_cpu_offset(cpu);
+#endif
         per_cpu(kernel_stack, cpu) =
                 (unsigned long)task_stack_page(idle) -
                 KERNEL_STACK_OFFSET + THREAD_SIZE;
-#endif
         early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
         initial_code = (unsigned long)start_secondary;
         stack_start  = idle->thread.sp;
@@ -1379,7 +1387,7 @@ static inline void mwait_play_dead(void)
 
         if (!this_cpu_has(X86_FEATURE_MWAIT))
                 return;
-        if (!this_cpu_has(X86_FEATURE_CLFLSH))
+        if (!this_cpu_has(X86_FEATURE_CLFLUSH))
                 return;
         if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF)
                 return;
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 24d3c91e9812..bf7ef5ce29df 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -23,7 +23,7 @@
 #include <asm/time.h>
 
 #ifdef CONFIG_X86_64
-DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
+__visible DEFINE_VVAR(volatile unsigned long, jiffies) = INITIAL_JIFFIES;
 #endif
 
 unsigned long profile_pc(struct pt_regs *regs)
@@ -62,7 +62,7 @@ static irqreturn_t timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction irq0  = {
         .handler = timer_interrupt,
-        .flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
+        .flags = IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
         .name = "timer"
 };
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index c6976257eff5..e5503d8aec1d 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -263,7 +263,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
                 F(TSC) | F(MSR) | F(PAE) | F(MCE) |
                 F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
                 F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
-                F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
+                F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLUSH) |
                 0 /* Reserved, DS, ACPI */ | F(MMX) |
                 F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
                 0 /* HTT, TM, Reserved, PBE */;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index e50425d0f5f7..9b531351a587 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2672,6 +2672,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
                         break;
                 }
 
+                drop_large_spte(vcpu, iterator.sptep);
                 if (!is_shadow_present_pte(*iterator.sptep)) {
                         u64 base_addr = iterator.addr;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index e81df8fce027..2de1bc09a8d4 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3002,10 +3002,8 @@ static int cr8_write_interception(struct vcpu_svm *svm)
         u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
         /* instruction emulation calls kvm_set_cr8() */
         r = cr_interception(svm);
-        if (irqchip_in_kernel(svm->vcpu.kvm)) {
-                clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+        if (irqchip_in_kernel(svm->vcpu.kvm))
                 return r;
-        }
         if (cr8_prev <= kvm_get_cr8(&svm->vcpu))
                 return r;
         kvm_run->exit_reason = KVM_EXIT_SET_TPR;
@@ -3567,6 +3565,8 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
         if (is_guest_mode(vcpu) && (vcpu->arch.hflags & HF_VINTR_MASK))
                 return;
 
+        clr_cr_intercept(svm, INTERCEPT_CR8_WRITE);
+
         if (irr == -1)
                 return;
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a06f101ef64b..392752834751 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6688,7 +6688,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
                 else if (is_page_fault(intr_info))
                         return enable_ept;
                 else if (is_no_device(intr_info) &&
-                         !(nested_read_cr0(vmcs12) & X86_CR0_TS))
+                         !(vmcs12->guest_cr0 & X86_CR0_TS))
                         return 0;
                 return vmcs12->exception_bitmap &
                                 (1u << (intr_info & INTR_INFO_VECTOR_MASK));
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 39c28f09dfd5..2b8578432d5b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6186,7 +6186,7 @@ static int complete_emulated_mmio(struct kvm_vcpu *vcpu)
                 frag->len -= len;
         }
 
-        if (vcpu->mmio_cur_fragment == vcpu->mmio_nr_fragments) {
+        if (vcpu->mmio_cur_fragment >= vcpu->mmio_nr_fragments) {
                 vcpu->mmio_needed = 0;
 
                 /* FIXME: return into emulator if single-stepping.  */
diff --git a/arch/x86/lib/hash.c b/arch/x86/lib/hash.c
index 3056702e81fb..ff4fa51a5b1f 100644
--- a/arch/x86/lib/hash.c
+++ b/arch/x86/lib/hash.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/hash.h>
+#include <linux/init.h>
 
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
@@ -39,7 +40,11 @@
 
 static inline u32 crc32_u32(u32 crc, u32 val)
 {
+#ifdef CONFIG_AS_CRC32
         asm ("crc32l %1,%0\n" : "+r" (crc) : "rm" (val));
+#else
+        asm (".byte 0xf2, 0x0f, 0x38, 0xf1, 0xc1" : "+a" (crc) : "c" (val));
+#endif
         return crc;
 }
 
@@ -49,19 +54,18 @@ static u32 intel_crc4_2_hash(const void *data, u32 len, u32 seed)
         u32 i, tmp = 0;
 
         for (i = 0; i < len / 4; i++)
-                seed = crc32_u32(*p32++, seed);
+                seed = crc32_u32(seed, *p32++);
 
-        switch (3 - (len & 0x03)) {
-        case 0:
+        switch (len & 3) {
+        case 3:
                 tmp |= *((const u8 *) p32 + 2) << 16;
                 /* fallthrough */
-        case 1:
+        case 2:
                 tmp |= *((const u8 *) p32 + 1) << 8;
                 /* fallthrough */
-        case 2:
+        case 1:
                 tmp |= *((const u8 *) p32);
-                seed = crc32_u32(tmp, seed);
-        default:
+                seed = crc32_u32(seed, tmp);
                 break;
         }
 
@@ -74,12 +78,12 @@ static u32 intel_crc4_2_hash2(const u32 *data, u32 len, u32 seed)
         u32 i;
 
         for (i = 0; i < len; i++)
-                seed = crc32_u32(*p32++, seed);
+                seed = crc32_u32(seed, *p32++);
 
         return seed;
 }
 
-void setup_arch_fast_hash(struct fast_hash_ops *ops)
+void __init setup_arch_fast_hash(struct fast_hash_ops *ops)
 {
         if (cpu_has_xmm4_2) {
                 ops->hash  = intel_crc4_2_hash;
diff --git a/arch/x86/lib/memcpy_32.c b/arch/x86/lib/memcpy_32.c
index e78761d6b7f8..a404b4b75533 100644
--- a/arch/x86/lib/memcpy_32.c
+++ b/arch/x86/lib/memcpy_32.c
@@ -4,7 +4,7 @@
 #undef memcpy
 #undef memset
 
-void *memcpy(void *to, const void *from, size_t n)
+__visible void *memcpy(void *to, const void *from, size_t n)
 {
 #ifdef CONFIG_X86_USE_3DNOW
         return __memcpy3d(to, from, n);
@@ -14,13 +14,13 @@ void *memcpy(void *to, const void *from, size_t n)
 }
 EXPORT_SYMBOL(memcpy);
 
-void *memset(void *s, int c, size_t count)
+__visible void *memset(void *s, int c, size_t count)
 {
         return __memset(s, c, count);
 }
 EXPORT_SYMBOL(memset);
 
-void *memmove(void *dest, const void *src, size_t n)
+__visible void *memmove(void *dest, const void *src, size_t n)
 {
         int d0,d1,d2,d3,d4,d5;
         char *ret = dest;
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 8f8eebdca7d4..db9db446b71a 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -8,7 +8,7 @@ struct msr *msrs_alloc(void)
 
         msrs = alloc_percpu(struct msr);
         if (!msrs) {
-                pr_warning("%s: error allocating msrs\n", __func__);
+                pr_warn("%s: error allocating msrs\n", __func__);
                 return NULL;
         }
 
@@ -21,3 +21,90 @@ void msrs_free(struct msr *msrs)
         free_percpu(msrs);
 }
 EXPORT_SYMBOL(msrs_free);
+
+/**
+ * Read an MSR with error handling
+ *
+ * @msr: MSR to read
+ * @m: value to read into
+ *
+ * It returns read data only on success, otherwise it doesn't change the output
+ * argument @m.
+ *
+ */
+int msr_read(u32 msr, struct msr *m)
+{
+        int err;
+        u64 val;
+
+        err = rdmsrl_safe(msr, &val);
+        if (!err)
+                m->q = val;
+
+        return err;
+}
+
+/**
+ * Write an MSR with error handling
+ *
+ * @msr: MSR to write
+ * @m: value to write
+ */
+int msr_write(u32 msr, struct msr *m)
+{
+        return wrmsrl_safe(msr, m->q);
+}
+
+static inline int __flip_bit(u32 msr, u8 bit, bool set)
+{
+        struct msr m, m1;
+        int err = -EINVAL;
+
+        if (bit > 63)
+                return err;
+
+        err = msr_read(msr, &m);
+        if (err)
+                return err;
+
+        m1 = m;
+        if (set)
+                m1.q |=  BIT_64(bit);
+        else
+                m1.q &= ~BIT_64(bit);
+
+        if (m1.q == m.q)
+                return 0;
+
+        err = msr_write(msr, &m);
+        if (err)
+                return err;
+
+        return 1;
+}
+
+/**
+ * Set @bit in a MSR @msr.
+ *
+ * Retval:
+ * < 0: An error was encountered.
+ * = 0: Bit was already set.
+ * > 0: Hardware accepted the MSR write.
+ */
+int msr_set_bit(u32 msr, u8 bit)
+{
+        return __flip_bit(msr, bit, true);
+}
+
+/**
+ * Clear @bit in a MSR @msr.
+ *
+ * Retval:
+ * < 0: An error was encountered.
+ * = 0: Bit was already cleared.
+ * > 0: Hardware accepted the MSR write.
+ */
+int msr_clear_bit(u32 msr, u8 bit)
+{
+        return __flip_bit(msr, bit, false);
+}
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 0002a3a33081..20621d753d5f 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -30,6 +30,7 @@ struct pg_state {
         unsigned long start_address;
         unsigned long current_address;
         const struct addr_marker *marker;
+        bool to_dmesg;
 };
 
 struct addr_marker {
@@ -88,10 +89,28 @@ static struct addr_marker address_markers[] = {
 #define PUD_LEVEL_MULT (PTRS_PER_PMD * PMD_LEVEL_MULT)
 #define PGD_LEVEL_MULT (PTRS_PER_PUD * PUD_LEVEL_MULT)
 
+#define pt_dump_seq_printf(m, to_dmesg, fmt, args...)           \
+({                                                              \
+        if (to_dmesg)                                   \
+                printk(KERN_INFO fmt, ##args);                  \
+        else                                                    \
+                if (m)                                          \
+                        seq_printf(m, fmt, ##args);             \
+})
+
+#define pt_dump_cont_printf(m, to_dmesg, fmt, args...)          \
+({                                                              \
+        if (to_dmesg)                                   \
+                printk(KERN_CONT fmt, ##args);                  \
+        else                                                    \
+                if (m)                                          \
+                        seq_printf(m, fmt, ##args);             \
+})
+
 /*
  * Print a readable form of a pgprot_t to the seq_file
  */
-static void printk_prot(struct seq_file *m, pgprot_t prot, int level)
+static void printk_prot(struct seq_file *m, pgprot_t prot, int level, bool dmsg)
 {
         pgprotval_t pr = pgprot_val(prot);
         static const char * const level_name[] =
@@ -99,47 +118,47 @@ static void printk_prot(struct seq_file *m, pgprot_t prot, int level)
 
         if (!pgprot_val(prot)) {
                 /* Not present */
-                seq_printf(m, "                          ");
+                pt_dump_cont_printf(m, dmsg, "                          ");
         } else {
                 if (pr & _PAGE_USER)
-                        seq_printf(m, "USR ");
+                        pt_dump_cont_printf(m, dmsg, "USR ");
                 else
-                        seq_printf(m, "    ");
+                        pt_dump_cont_printf(m, dmsg, "    ");
                 if (pr & _PAGE_RW)
-                        seq_printf(m, "RW ");
+                        pt_dump_cont_printf(m, dmsg, "RW ");
                 else
-                        seq_printf(m, "ro ");
+                        pt_dump_cont_printf(m, dmsg, "ro ");
                 if (pr & _PAGE_PWT)
-                        seq_printf(m, "PWT ");
+                        pt_dump_cont_printf(m, dmsg, "PWT ");
                 else
-                        seq_printf(m, "    ");
+                        pt_dump_cont_printf(m, dmsg, "    ");
                 if (pr & _PAGE_PCD)
-                        seq_printf(m, "PCD ");
+                        pt_dump_cont_printf(m, dmsg, "PCD ");
                 else
-                        seq_printf(m, "    ");
+                        pt_dump_cont_printf(m, dmsg, "    ");
 
                 /* Bit 9 has a different meaning on level 3 vs 4 */
                 if (level <= 3) {
                         if (pr & _PAGE_PSE)
-                                seq_printf(m, "PSE ");
+                                pt_dump_cont_printf(m, dmsg, "PSE ");
                         else
-                                seq_printf(m, "    ");
+                                pt_dump_cont_printf(m, dmsg, "    ");
                 } else {
                         if (pr & _PAGE_PAT)
-                                seq_printf(m, "pat ");
+                                pt_dump_cont_printf(m, dmsg, "pat ");
                         else
-                                seq_printf(m, "    ");
+                                pt_dump_cont_printf(m, dmsg, "    ");
                 }
                 if (pr & _PAGE_GLOBAL)
-                        seq_printf(m, "GLB ");
+                        pt_dump_cont_printf(m, dmsg, "GLB ");
                 else
-                        seq_printf(m, "    ");
+                        pt_dump_cont_printf(m, dmsg, "    ");
                 if (pr & _PAGE_NX)
-                        seq_printf(m, "NX ");
+                        pt_dump_cont_printf(m, dmsg, "NX ");
                 else
-                        seq_printf(m, "x  ");
+                        pt_dump_cont_printf(m, dmsg, "x  ");
         }
-        seq_printf(m, "%s\n", level_name[level]);
+        pt_dump_cont_printf(m, dmsg, "%s\n", level_name[level]);
 }
 
 /*
@@ -178,7 +197,8 @@ static void note_page(struct seq_file *m, struct pg_state *st,
                 st->current_prot = new_prot;
                 st->level = level;
                 st->marker = address_markers;
-                seq_printf(m, "---[ %s ]---\n", st->marker->name);
+                pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
+                                   st->marker->name);
         } else if (prot != cur || level != st->level ||
                    st->current_address >= st->marker[1].start_address) {
                 const char *unit = units;
@@ -188,17 +208,17 @@ static void note_page(struct seq_file *m, struct pg_state *st,
                 /*
                  * Now print the actual finished series
                  */
-                seq_printf(m, "0x%0*lx-0x%0*lx   ",
-                           width, st->start_address,
-                           width, st->current_address);
+                pt_dump_seq_printf(m, st->to_dmesg,  "0x%0*lx-0x%0*lx   ",
+                                   width, st->start_address,
+                                   width, st->current_address);
 
                 delta = (st->current_address - st->start_address) >> 10;
                 while (!(delta & 1023) && unit[1]) {
                         delta >>= 10;
                         unit++;
                 }
-                seq_printf(m, "%9lu%c ", delta, *unit);
-                printk_prot(m, st->current_prot, st->level);
+                pt_dump_cont_printf(m, st->to_dmesg, "%9lu%c ", delta, *unit);
+                printk_prot(m, st->current_prot, st->level, st->to_dmesg);
 
                 /*
                  * We print markers for special areas of address space,
@@ -207,7 +227,8 @@ static void note_page(struct seq_file *m, struct pg_state *st,
                  */
                 if (st->current_address >= st->marker[1].start_address) {
                         st->marker++;
-                        seq_printf(m, "---[ %s ]---\n", st->marker->name);
+                        pt_dump_seq_printf(m, st->to_dmesg, "---[ %s ]---\n",
+                                           st->marker->name);
                 }
 
                 st->start_address = st->current_address;
@@ -296,7 +317,7 @@ static void walk_pud_level(struct seq_file *m, struct pg_state *st, pgd_t addr,
 #define pgd_none(a)  pud_none(__pud(pgd_val(a)))
 #endif
 
-static void walk_pgd_level(struct seq_file *m)
+void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd)
 {
 #ifdef CONFIG_X86_64
         pgd_t *start = (pgd_t *) &init_level4_pgt;
@@ -304,9 +325,12 @@ static void walk_pgd_level(struct seq_file *m)
         pgd_t *start = swapper_pg_dir;
 #endif
         int i;
-        struct pg_state st;
+        struct pg_state st = {};
 
-        memset(&st, 0, sizeof(st));
+        if (pgd) {
+                start = pgd;
+                st.to_dmesg = true;
+        }
 
         for (i = 0; i < PTRS_PER_PGD; i++) {
                 st.current_address = normalize_addr(i * PGD_LEVEL_MULT);
@@ -331,7 +355,7 @@ static void walk_pgd_level(struct seq_file *m)
 
 static int ptdump_show(struct seq_file *m, void *v)
 {
-        walk_pgd_level(m);
+        ptdump_walk_pgd_level(m, NULL);
         return 0;
 }
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 6dea040cc3a1..8e5722992677 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -584,8 +584,13 @@ show_fault_oops(struct pt_regs *regs, unsigned long error_code,
 
         if (error_code & PF_INSTR) {
                 unsigned int level;
+                pgd_t *pgd;
+                pte_t *pte;
 
-                pte_t *pte = lookup_address(address, &level);
+                pgd = __va(read_cr3() & PHYSICAL_PAGE_MASK);
+                pgd += pgd_index(address);
+
+                pte = lookup_address_in_pgd(pgd, address, &level);
 
                 if (pte && pte_present(*pte) && !pte_exec(*pte))
                         printk(nx_warning, from_kuid(&init_user_ns, current_uid()));
@@ -1020,13 +1025,17 @@ static inline bool smap_violation(int error_code, struct pt_regs *regs)
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
  * routines.
+ *
+ * This function must have noinline because both callers
+ * {,trace_}do_page_fault() have notrace on. Having this an actual function
+ * guarantees there's a function trace entry.
  */
-static void __kprobes
-__do_page_fault(struct pt_regs *regs, unsigned long error_code)
+static void __kprobes noinline
+__do_page_fault(struct pt_regs *regs, unsigned long error_code,
+                unsigned long address)
 {
         struct vm_area_struct *vma;
         struct task_struct *tsk;
-        unsigned long address;
         struct mm_struct *mm;
         int fault;
         unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
@@ -1034,9 +1043,6 @@ __do_page_fault(struct pt_regs *regs, unsigned long error_code)
         tsk = current;
         mm = tsk->mm;
 
-        /* Get the faulting address: */
-        address = read_cr2();
-
         /*
          * Detect and handle instructions that would cause a page fault for
          * both a tracked kernel page and a userspace page.
@@ -1248,32 +1254,50 @@ good_area:
         up_read(&mm->mmap_sem);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+        unsigned long address = read_cr2(); /* Get the faulting address */
         enum ctx_state prev_state;
 
+        /*
+         * We must have this function tagged with __kprobes, notrace and call
+         * read_cr2() before calling anything else. To avoid calling any kind
+         * of tracing machinery before we've observed the CR2 value.
+         *
+         * exception_{enter,exit}() contain all sorts of tracepoints.
+         */
+
         prev_state = exception_enter();
-        __do_page_fault(regs, error_code);
+        __do_page_fault(regs, error_code, address);
         exception_exit(prev_state);
 }
 
-static void trace_page_fault_entries(struct pt_regs *regs,
+#ifdef CONFIG_TRACING
+static void trace_page_fault_entries(unsigned long address, struct pt_regs *regs,
                                      unsigned long error_code)
 {
         if (user_mode(regs))
-                trace_page_fault_user(read_cr2(), regs, error_code);
+                trace_page_fault_user(address, regs, error_code);
         else
-                trace_page_fault_kernel(read_cr2(), regs, error_code);
+                trace_page_fault_kernel(address, regs, error_code);
 }
 
-dotraplinkage void __kprobes
+dotraplinkage void __kprobes notrace
 trace_do_page_fault(struct pt_regs *regs, unsigned long error_code)
 {
+        /*
+         * The exception_enter and tracepoint processing could
+         * trigger another page faults (user space callchain
+         * reading) and destroy the original cr2 value, so read
+         * the faulting address now.
+         */
+        unsigned long address = read_cr2();
         enum ctx_state prev_state;
 
         prev_state = exception_enter();
-        trace_page_fault_entries(regs, error_code);
-        __do_page_fault(regs, error_code);
+        trace_page_fault_entries(address, regs, error_code);
+        __do_page_fault(regs, error_code, address);
         exception_exit(prev_state);
 }
+#endif /* CONFIG_TRACING */
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index b3b19f46c016..ae242a7c11c7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -126,8 +126,8 @@ within(unsigned long addr, unsigned long start, unsigned long end)
  * @vaddr:      virtual start address
  * @size:       number of bytes to flush
  *
- * clflush is an unordered instruction which needs fencing with mfence
- * to avoid ordering issues.
+ * clflushopt is an unordered instruction which needs fencing with mfence or
+ * sfence to avoid ordering issues.
  */
 void clflush_cache_range(void *vaddr, unsigned int size)
 {
@@ -136,11 +136,11 @@ void clflush_cache_range(void *vaddr, unsigned int size)
         mb();
 
         for (; vaddr < vend; vaddr += boot_cpu_data.x86_clflush_size)
-                clflush(vaddr);
+                clflushopt(vaddr);
         /*
          * Flush any possible final partial cacheline:
          */
-        clflush(vend);
+        clflushopt(vend);
 
         mb();
 }
@@ -323,8 +323,12 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
         return prot;
 }
 
-static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
-                                      unsigned int *level)
+/*
+ * Lookup the page table entry for a virtual address in a specific pgd.
+ * Return a pointer to the entry and the level of the mapping.
+ */
+pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
+                             unsigned int *level)
 {
         pud_t *pud;
         pmd_t *pmd;
@@ -365,7 +369,7 @@ static pte_t *__lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
  */
 pte_t *lookup_address(unsigned long address, unsigned int *level)
 {
-        return __lookup_address_in_pgd(pgd_offset_k(address), address, level);
+        return lookup_address_in_pgd(pgd_offset_k(address), address, level);
 }
 EXPORT_SYMBOL_GPL(lookup_address);
 
@@ -373,7 +377,7 @@ static pte_t *_lookup_address_cpa(struct cpa_data *cpa, unsigned long address,
                                   unsigned int *level)
 {
         if (cpa->pgd)
-                return __lookup_address_in_pgd(cpa->pgd + pgd_index(address),
+                return lookup_address_in_pgd(cpa->pgd + pgd_index(address),
                                                address, level);
 
         return lookup_address(address, level);
@@ -692,6 +696,18 @@ static bool try_to_free_pmd_page(pmd_t *pmd)
         return true;
 }
 
+static bool try_to_free_pud_page(pud_t *pud)
+{
+        int i;
+
+        for (i = 0; i < PTRS_PER_PUD; i++)
+                if (!pud_none(pud[i]))
+                        return false;
+
+        free_page((unsigned long)pud);
+        return true;
+}
+
 static bool unmap_pte_range(pmd_t *pmd, unsigned long start, unsigned long end)
 {
         pte_t *pte = pte_offset_kernel(pmd, start);
@@ -805,6 +821,16 @@ static void unmap_pud_range(pgd_t *pgd, unsigned long start, unsigned long end)
          */
 }
 
+static void unmap_pgd_range(pgd_t *root, unsigned long addr, unsigned long end)
+{
+        pgd_t *pgd_entry = root + pgd_index(addr);
+
+        unmap_pud_range(pgd_entry, addr, end);
+
+        if (try_to_free_pud_page((pud_t *)pgd_page_vaddr(*pgd_entry)))
+                pgd_clear(pgd_entry);
+}
+
 static int alloc_pte_page(pmd_t *pmd)
 {
         pte_t *pte = (pte_t *)get_zeroed_page(GFP_KERNEL | __GFP_NOTRACK);
@@ -999,9 +1025,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 {
         pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
-        bool allocd_pgd = false;
-        pgd_t *pgd_entry;
         pud_t *pud = NULL;      /* shut up gcc */
+        pgd_t *pgd_entry;
         int ret;
 
         pgd_entry = cpa->pgd + pgd_index(addr);
@@ -1015,7 +1040,6 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
                         return -1;
 
                 set_pgd(pgd_entry, __pgd(__pa(pud) | _KERNPG_TABLE));
-                allocd_pgd = true;
         }
 
         pgprot_val(pgprot) &= ~pgprot_val(cpa->mask_clr);
@@ -1023,19 +1047,11 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 
         ret = populate_pud(cpa, addr, pgd_entry, pgprot);
         if (ret < 0) {
-                unmap_pud_range(pgd_entry, addr,
+                unmap_pgd_range(cpa->pgd, addr,
                                 addr + (cpa->numpages << PAGE_SHIFT));
-
-                if (allocd_pgd) {
-                        /*
-                         * If I allocated this PUD page, I can just as well
-                         * free it in this error path.
-                         */
-                        pgd_clear(pgd_entry);
-                        free_page((unsigned long)pud);
-                }
                 return ret;
         }
+
         cpa->numpages = ret;
         return 0;
 }
@@ -1377,10 +1393,10 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
         cache = cache_attr(mask_set);
 
         /*
-         * On success we use clflush, when the CPU supports it to
-         * avoid the wbindv. If the CPU does not support it and in the
+         * On success we use CLFLUSH, when the CPU supports it to
+         * avoid the WBINVD. If the CPU does not support it and in the
          * error case we fall back to cpa_flush_all (which uses
-         * wbindv):
+         * WBINVD):
          */
         if (!ret && cpu_has_clflush) {
                 if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
@@ -1861,6 +1877,12 @@ out:
         return retval;
 }
 
+void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
+                               unsigned numpages)
+{
+        unmap_pgd_range(root, address, address + (numpages << PAGE_SHIFT));
+}
+
 /*
  * The testcases use internal knowledge of the implementation that shouldn't
  * be exposed to the rest of the kernel. Include these directly here.
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 1953e9c9391a..66338a60aa6e 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -52,12 +52,18 @@ void __init acpi_numa_slit_init(struct acpi_table_slit *slit)
         int i, j;
 
         for (i = 0; i < slit->locality_count; i++) {
-                if (pxm_to_node(i) == NUMA_NO_NODE)
+                const int from_node = pxm_to_node(i);
+
+                if (from_node == NUMA_NO_NODE)
                         continue;
+
                 for (j = 0; j < slit->locality_count; j++) {
-                        if (pxm_to_node(j) == NUMA_NO_NODE)
+                        const int to_node = pxm_to_node(j);
+
+                        if (to_node == NUMA_NO_NODE)
                                 continue;
-                        numa_set_distance(pxm_to_node(i), pxm_to_node(j),
+
+                        numa_set_distance(from_node, to_node,
                                 slit->entry[slit->locality_count * i + j]);
                 }
         }
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 877b9a1b2152..01495755701b 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -140,7 +140,7 @@ bpf_slow_path_byte_msh:
         push    %r9;                                            \
         push    SKBDATA;                                        \
 /* rsi already has offset */                                    \
-        mov     $SIZE,%ecx;     /* size */                      \
+        mov     $SIZE,%edx;     /* size */                      \
         call    bpf_internal_load_pointer_neg_helper;           \
         test    %rax,%rax;                                      \
         pop     SKBDATA;                                        \
diff --git a/arch/x86/platform/efi/Makefile b/arch/x86/platform/efi/Makefile
index b7b0b35c1981..d51045afcaaf 100644
--- a/arch/x86/platform/efi/Makefile
+++ b/arch/x86/platform/efi/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_EFI)               += efi.o efi_$(BITS).o efi_stub_$(BITS).o
 obj-$(CONFIG_ACPI_BGRT) += efi-bgrt.o
 obj-$(CONFIG_EARLY_PRINTK_EFI)  += early_printk.o
+obj-$(CONFIG_EFI_MIXED)         += efi_thunk_$(BITS).o
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 1a201ac7cef8..3781dd39e8bd 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -52,6 +52,7 @@
 #include <asm/tlbflush.h>
 #include <asm/x86_init.h>
 #include <asm/rtc.h>
+#include <asm/uv/uv.h>
 
 #define EFI_DEBUG
 
@@ -67,9 +68,7 @@ struct efi_memory_map memmap;
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
-unsigned long x86_efi_facility;
-
-static __initdata efi_config_table_type_t arch_tables[] = {
+static efi_config_table_type_t arch_tables[] __initdata = {
 #ifdef CONFIG_X86_UV
         {UV_SYSTEM_TABLE_GUID, "UVsystab", &efi.uv_systab},
 #endif
@@ -78,16 +77,7 @@ static __initdata efi_config_table_type_t arch_tables[] = {
 
 u64 efi_setup;          /* efi setup_data physical address */
 
-/*
- * Returns 1 if 'facility' is enabled, 0 otherwise.
- */
-int efi_enabled(int facility)
-{
-        return test_bit(facility, &x86_efi_facility) != 0;
-}
-EXPORT_SYMBOL(efi_enabled);
-
-static bool __initdata disable_runtime = false;
+static bool disable_runtime __initdata = false;
 static int __init setup_noefi(char *arg)
 {
         disable_runtime = true;
@@ -256,27 +246,12 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
         return status;
 }
 
-static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
-                                             efi_time_cap_t *tc)
-{
-        unsigned long flags;
-        efi_status_t status;
-
-        spin_lock_irqsave(&rtc_lock, flags);
-        efi_call_phys_prelog();
-        status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
-                                virt_to_phys(tc));
-        efi_call_phys_epilog();
-        spin_unlock_irqrestore(&rtc_lock, flags);
-        return status;
-}
-
 int efi_set_rtc_mmss(const struct timespec *now)
 {
         unsigned long nowtime = now->tv_sec;
-        efi_status_t    status;
-        efi_time_t      eft;
-        efi_time_cap_t  cap;
+        efi_status_t    status;
+        efi_time_t      eft;
+        efi_time_cap_t  cap;
         struct rtc_time tm;
 
         status = efi.get_time(&eft, &cap);
@@ -294,9 +269,8 @@ int efi_set_rtc_mmss(const struct timespec *now)
                 eft.second = tm.tm_sec;
                 eft.nanosecond = 0;
         } else {
-                printk(KERN_ERR
-                       "%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n",
-                       __FUNCTION__, nowtime);
+                pr_err("%s: Invalid EFI RTC value: write of %lx to EFI RTC failed\n",
+                       __func__, nowtime);
                 return -1;
         }
 
@@ -412,8 +386,7 @@ static void __init print_efi_memmap(void)
              p < memmap.map_end;
              p += memmap.desc_size, i++) {
                 md = p;
-                pr_info("mem%02u: type=%u, attr=0x%llx, "
-                        "range=[0x%016llx-0x%016llx) (%lluMB)\n",
+                pr_info("mem%02u: type=%u, attr=0x%llx, range=[0x%016llx-0x%016llx) (%lluMB)\n",
                         i, md->type, md->attribute, md->phys_addr,
                         md->phys_addr + (md->num_pages << EFI_PAGE_SHIFT),
                         (md->num_pages >> (20 - EFI_PAGE_SHIFT)));
@@ -445,9 +418,8 @@ void __init efi_reserve_boot_services(void)
                         memblock_is_region_reserved(start, size)) {
                         /* Could not reserve, skip it */
                         md->num_pages = 0;
-                        memblock_dbg("Could not reserve boot range "
-                                        "[0x%010llx-0x%010llx]\n",
-                                                start, start+size-1);
+                        memblock_dbg("Could not reserve boot range [0x%010llx-0x%010llx]\n",
+                                     start, start+size-1);
                 } else
                         memblock_reserve(start, size);
         }
@@ -455,7 +427,7 @@ void __init efi_reserve_boot_services(void)
 
 void __init efi_unmap_memmap(void)
 {
-        clear_bit(EFI_MEMMAP, &x86_efi_facility);
+        clear_bit(EFI_MEMMAP, &efi.flags);
         if (memmap.map) {
                 early_iounmap(memmap.map, memmap.nr_map * memmap.desc_size);
                 memmap.map = NULL;
@@ -466,9 +438,6 @@ void __init efi_free_boot_services(void)
 {
         void *p;
 
-        if (!efi_is_native())
-                return;
-
         for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
                 efi_memory_desc_t *md = p;
                 unsigned long long start = md->phys_addr;
@@ -583,45 +552,82 @@ static int __init efi_systab_init(void *phys)
                 return -EINVAL;
         }
         if ((efi.systab->hdr.revision >> 16) == 0)
-                pr_err("Warning: System table version "
-                       "%d.%02d, expected 1.00 or greater!\n",
+                pr_err("Warning: System table version %d.%02d, expected 1.00 or greater!\n",
                        efi.systab->hdr.revision >> 16,
                        efi.systab->hdr.revision & 0xffff);
 
+        set_bit(EFI_SYSTEM_TABLES, &efi.flags);
+
         return 0;
 }
 
-static int __init efi_runtime_init(void)
+static int __init efi_runtime_init32(void)
 {
-        efi_runtime_services_t *runtime;
+        efi_runtime_services_32_t *runtime;
+
+        runtime = early_ioremap((unsigned long)efi.systab->runtime,
+                        sizeof(efi_runtime_services_32_t));
+        if (!runtime) {
+                pr_err("Could not map the runtime service table!\n");
+                return -ENOMEM;
+        }
 
         /*
-         * Check out the runtime services table. We need to map
-         * the runtime services table so that we can grab the physical
-         * address of several of the EFI runtime functions, needed to
-         * set the firmware into virtual mode.
+         * We will only need *early* access to the following two
+         * EFI runtime services before set_virtual_address_map
+         * is invoked.
          */
+        efi_phys.set_virtual_address_map =
+                        (efi_set_virtual_address_map_t *)
+                        (unsigned long)runtime->set_virtual_address_map;
+        early_iounmap(runtime, sizeof(efi_runtime_services_32_t));
+
+        return 0;
+}
+
+static int __init efi_runtime_init64(void)
+{
+        efi_runtime_services_64_t *runtime;
+
         runtime = early_ioremap((unsigned long)efi.systab->runtime,
-                                sizeof(efi_runtime_services_t));
+                        sizeof(efi_runtime_services_64_t));
         if (!runtime) {
                 pr_err("Could not map the runtime service table!\n");
                 return -ENOMEM;
         }
+
         /*
-         * We will only need *early* access to the following
-         * two EFI runtime services before set_virtual_address_map
+         * We will only need *early* access to the following two
+         * EFI runtime services before set_virtual_address_map
          * is invoked.
          */
-        efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
         efi_phys.set_virtual_address_map =
-                (efi_set_virtual_address_map_t *)
-                runtime->set_virtual_address_map;
+                        (efi_set_virtual_address_map_t *)
+                        (unsigned long)runtime->set_virtual_address_map;
+        early_iounmap(runtime, sizeof(efi_runtime_services_64_t));
+
+        return 0;
+}
+
+static int __init efi_runtime_init(void)
+{
+        int rv;
+
         /*
-         * Make efi_get_time can be called before entering
-         * virtual mode.
+         * Check out the runtime services table. We need to map
+         * the runtime services table so that we can grab the physical
+         * address of several of the EFI runtime functions, needed to
+         * set the firmware into virtual mode.
          */
-        efi.get_time = phys_efi_get_time;
-        early_iounmap(runtime, sizeof(efi_runtime_services_t));
+        if (efi_enabled(EFI_64BIT))
+                rv = efi_runtime_init64();
+        else
+                rv = efi_runtime_init32();
+
+        if (rv)
+                return rv;
+
+        set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
 
         return 0;
 }
@@ -640,6 +646,8 @@ static int __init efi_memmap_init(void)
         if (add_efi_memmap)
                 do_add_efi_memmap();
 
+        set_bit(EFI_MEMMAP, &efi.flags);
+
         return 0;
 }
 
@@ -722,7 +730,7 @@ void __init efi_init(void)
         if (efi_systab_init(efi_phys.systab))
                 return;
 
-        set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
+        set_bit(EFI_SYSTEM_TABLES, &efi.flags);
 
         efi.config_table = (unsigned long)efi.systab->tables;
         efi.fw_vendor    = (unsigned long)efi.systab->fw_vendor;
@@ -750,24 +758,21 @@ void __init efi_init(void)
         if (efi_config_init(arch_tables))
                 return;
 
-        set_bit(EFI_CONFIG_TABLES, &x86_efi_facility);
-
         /*
          * Note: We currently don't support runtime services on an EFI
          * that doesn't match the kernel 32/64-bit mode.
          */
 
-        if (!efi_is_native())
+        if (!efi_runtime_supported())
                 pr_info("No EFI runtime due to 32/64-bit mismatch with kernel\n");
         else {
                 if (disable_runtime || efi_runtime_init())
                         return;
-                set_bit(EFI_RUNTIME_SERVICES, &x86_efi_facility);
         }
         if (efi_memmap_init())
                 return;
 
-        set_bit(EFI_MEMMAP, &x86_efi_facility);
+        set_bit(EFI_MEMMAP, &efi.flags);
 
         print_efi_memmap();
 }
@@ -844,6 +849,22 @@ void __init old_map_region(efi_memory_desc_t *md)
                        (unsigned long long)md->phys_addr);
 }
 
+static void native_runtime_setup(void)
+{
+        efi.get_time = virt_efi_get_time;
+        efi.set_time = virt_efi_set_time;
+        efi.get_wakeup_time = virt_efi_get_wakeup_time;
+        efi.set_wakeup_time = virt_efi_set_wakeup_time;
+        efi.get_variable = virt_efi_get_variable;
+        efi.get_next_variable = virt_efi_get_next_variable;
+        efi.set_variable = virt_efi_set_variable;
+        efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
+        efi.reset_system = virt_efi_reset_system;
+        efi.query_variable_info = virt_efi_query_variable_info;
+        efi.update_capsule = virt_efi_update_capsule;
+        efi.query_capsule_caps = virt_efi_query_capsule_caps;
+}
+
 /* Merge contiguous regions of the same type and attribute */
 static void __init efi_merge_regions(void)
 {
@@ -891,8 +912,9 @@ static void __init get_systab_virt_addr(efi_memory_desc_t *md)
         }
 }
 
-static int __init save_runtime_map(void)
+static void __init save_runtime_map(void)
 {
+#ifdef CONFIG_KEXEC
         efi_memory_desc_t *md;
         void *tmp, *p, *q = NULL;
         int count = 0;
@@ -914,38 +936,44 @@ static int __init save_runtime_map(void)
         }
 
         efi_runtime_map_setup(q, count, memmap.desc_size);
+        return;
 
-        return 0;
 out:
         kfree(q);
-        return -ENOMEM;
+        pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+#endif
 }
 
-/*
- * Map efi regions which were passed via setup_data. The virt_addr is a fixed
- * addr which was used in first kernel of a kexec boot.
- */
-static void __init efi_map_regions_fixed(void)
+static void *realloc_pages(void *old_memmap, int old_shift)
 {
-        void *p;
-        efi_memory_desc_t *md;
+        void *ret;
 
-        for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
-                md = p;
-                efi_map_region_fixed(md); /* FIXME: add error handling */
-                get_systab_virt_addr(md);
-        }
+        ret = (void *)__get_free_pages(GFP_KERNEL, old_shift + 1);
+        if (!ret)
+                goto out;
 
+        /*
+         * A first-time allocation doesn't have anything to copy.
+         */
+        if (!old_memmap)
+                return ret;
+
+        memcpy(ret, old_memmap, PAGE_SIZE << old_shift);
+
+out:
+        free_pages((unsigned long)old_memmap, old_shift);
+        return ret;
 }
 
 /*
- * Map efi memory ranges for runtime serivce and update new_memmap with virtual
- * addresses.
+ * Map the efi memory ranges of the runtime services and update new_mmap with
+ * virtual addresses.
  */
-static void * __init efi_map_regions(int *count)
+static void * __init efi_map_regions(int *count, int *pg_shift)
 {
+        void *p, *new_memmap = NULL;
+        unsigned long left = 0;
         efi_memory_desc_t *md;
-        void *p, *tmp, *new_memmap = NULL;
 
         for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
                 md = p;
@@ -960,20 +988,80 @@ static void * __init efi_map_regions(int *count)
                 efi_map_region(md);
                 get_systab_virt_addr(md);
 
-                tmp = krealloc(new_memmap, (*count + 1) * memmap.desc_size,
-                               GFP_KERNEL);
-                if (!tmp)
-                        goto out;
-                new_memmap = tmp;
+                if (left < memmap.desc_size) {
+                        new_memmap = realloc_pages(new_memmap, *pg_shift);
+                        if (!new_memmap)
+                                return NULL;
+
+                        left += PAGE_SIZE << *pg_shift;
+                        (*pg_shift)++;
+                }
+
                 memcpy(new_memmap + (*count * memmap.desc_size), md,
                        memmap.desc_size);
+
+                left -= memmap.desc_size;
                 (*count)++;
         }
 
         return new_memmap;
-out:
-        kfree(new_memmap);
-        return NULL;
+}
+
+static void __init kexec_enter_virtual_mode(void)
+{
+#ifdef CONFIG_KEXEC
+        efi_memory_desc_t *md;
+        void *p;
+
+        efi.systab = NULL;
+
+        /*
+         * We don't do virtual mode, since we don't do runtime services, on
+         * non-native EFI
+         */
+        if (!efi_is_native()) {
+                efi_unmap_memmap();
+                return;
+        }
+
+        /*
+        * Map efi regions which were passed via setup_data. The virt_addr is a
+        * fixed addr which was used in first kernel of a kexec boot.
+        */
+        for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+                md = p;
+                efi_map_region_fixed(md); /* FIXME: add error handling */
+                get_systab_virt_addr(md);
+        }
+
+        save_runtime_map();
+
+        BUG_ON(!efi.systab);
+
+        efi_sync_low_kernel_mappings();
+
+        /*
+         * Now that EFI is in virtual mode, update the function
+         * pointers in the runtime service table to the new virtual addresses.
+         *
+         * Call EFI services through wrapper functions.
+         */
+        efi.runtime_version = efi_systab.hdr.revision;
+
+        native_runtime_setup();
+
+        efi.set_virtual_address_map = NULL;
+
+        if (efi_enabled(EFI_OLD_MEMMAP) && (__supported_pte_mask & _PAGE_NX))
+                runtime_code_page_mkexec();
+
+        /* clean DUMMY object */
+        efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
+                         EFI_VARIABLE_NON_VOLATILE |
+                         EFI_VARIABLE_BOOTSERVICE_ACCESS |
+                         EFI_VARIABLE_RUNTIME_ACCESS,
+                         0, NULL);
+#endif
 }
 
 /*
@@ -995,57 +1083,53 @@ out:
  *
  * Specially for kexec boot, efi runtime maps in previous kernel should
  * be passed in via setup_data. In that case runtime ranges will be mapped
- * to the same virtual addresses as the first kernel.
+ * to the same virtual addresses as the first kernel, see
+ * kexec_enter_virtual_mode().
  */
-void __init efi_enter_virtual_mode(void)
+static void __init __efi_enter_virtual_mode(void)
 {
-        efi_status_t status;
+        int count = 0, pg_shift = 0;
         void *new_memmap = NULL;
-        int err, count = 0;
+        efi_status_t status;
 
         efi.systab = NULL;
 
-        /*
-         * We don't do virtual mode, since we don't do runtime services, on
-         * non-native EFI
-         */
-        if (!efi_is_native()) {
-                efi_unmap_memmap();
+        efi_merge_regions();
+        new_memmap = efi_map_regions(&count, &pg_shift);
+        if (!new_memmap) {
+                pr_err("Error reallocating memory, EFI runtime non-functional!\n");
                 return;
         }
 
-        if (efi_setup) {
-                efi_map_regions_fixed();
-        } else {
-                efi_merge_regions();
-                new_memmap = efi_map_regions(&count);
-                if (!new_memmap) {
-                        pr_err("Error reallocating memory, EFI runtime non-functional!\n");
-                        return;
-                }
-        }
-
-        err = save_runtime_map();
-        if (err)
-                pr_err("Error saving runtime map, efi runtime on kexec non-functional!!\n");
+        save_runtime_map();
 
         BUG_ON(!efi.systab);
 
-        efi_setup_page_tables();
+        if (efi_setup_page_tables(__pa(new_memmap), 1 << pg_shift))
+                return;
+
         efi_sync_low_kernel_mappings();
+        efi_dump_pagetable();
 
-        if (!efi_setup) {
+        if (efi_is_native()) {
                 status = phys_efi_set_virtual_address_map(
-                        memmap.desc_size * count,
-                        memmap.desc_size,
-                        memmap.desc_version,
-                        (efi_memory_desc_t *)__pa(new_memmap));
-
-                if (status != EFI_SUCCESS) {
-                        pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
-                                 status);
-                        panic("EFI call to SetVirtualAddressMap() failed!");
-                }
+                                memmap.desc_size * count,
+                                memmap.desc_size,
+                                memmap.desc_version,
+                                (efi_memory_desc_t *)__pa(new_memmap));
+        } else {
+                status = efi_thunk_set_virtual_address_map(
+                                efi_phys.set_virtual_address_map,
+                                memmap.desc_size * count,
+                                memmap.desc_size,
+                                memmap.desc_version,
+                                (efi_memory_desc_t *)__pa(new_memmap));
+        }
+
+        if (status != EFI_SUCCESS) {
+                pr_alert("Unable to switch EFI into virtual mode (status=%lx)!\n",
+                         status);
+                panic("EFI call to SetVirtualAddressMap() failed!");
         }
 
         /*
@@ -1055,23 +1139,43 @@ void __init efi_enter_virtual_mode(void)
          * Call EFI services through wrapper functions.
          */
         efi.runtime_version = efi_systab.hdr.revision;
-        efi.get_time = virt_efi_get_time;
-        efi.set_time = virt_efi_set_time;
-        efi.get_wakeup_time = virt_efi_get_wakeup_time;
-        efi.set_wakeup_time = virt_efi_set_wakeup_time;
-        efi.get_variable = virt_efi_get_variable;
-        efi.get_next_variable = virt_efi_get_next_variable;
-        efi.set_variable = virt_efi_set_variable;
-        efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
-        efi.reset_system = virt_efi_reset_system;
+
+        if (efi_is_native())
+                native_runtime_setup();
+        else
+                efi_thunk_runtime_setup();
+
         efi.set_virtual_address_map = NULL;
-        efi.query_variable_info = virt_efi_query_variable_info;
-        efi.update_capsule = virt_efi_update_capsule;
-        efi.query_capsule_caps = virt_efi_query_capsule_caps;
 
         efi_runtime_mkexec();
 
-        kfree(new_memmap);
+        /*
+         * We mapped the descriptor array into the EFI pagetable above but we're
+         * not unmapping it here. Here's why:
+         *
+         * We're copying select PGDs from the kernel page table to the EFI page
+         * table and when we do so and make changes to those PGDs like unmapping
+         * stuff from them, those changes appear in the kernel page table and we
+         * go boom.
+         *
+         * From setup_real_mode():
+         *
+         * ...
+         * trampoline_pgd[0] = init_level4_pgt[pgd_index(__PAGE_OFFSET)].pgd;
+         *
+         * In this particular case, our allocation is in PGD 0 of the EFI page
+         * table but we've copied that PGD from PGD[272] of the EFI page table:
+         *
+         *      pgd_index(__PAGE_OFFSET = 0xffff880000000000) = 272
+         *
+         * where the direct memory mapping in kernel space is.
+         *
+         * new_memmap's VA comes from that direct mapping and thus clearing it,
+         * it would get cleared in the kernel page table too.
+         *
+         * efi_cleanup_page_tables(__pa(new_memmap), 1 << pg_shift);
+         */
+        free_pages((unsigned long)new_memmap, pg_shift);
 
         /* clean DUMMY object */
         efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
@@ -1081,6 +1185,14 @@ void __init efi_enter_virtual_mode(void)
                          0, NULL);
 }
 
+void __init efi_enter_virtual_mode(void)
+{
+        if (efi_setup)
+                kexec_enter_virtual_mode();
+        else
+                __efi_enter_virtual_mode();
+}
+
 /*
  * Convenience functions to obtain memory types and attributes
  */
@@ -1118,9 +1230,8 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 }
 
 /*
- * Some firmware has serious problems when using more than 50% of the EFI
- * variable store, i.e. it triggers bugs that can brick machines. Ensure that
- * we never use more than this safe limit.
+ * Some firmware implementations refuse to boot if there's insufficient space
+ * in the variable store. Ensure that we never use more than a safe limit.
  *
  * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
  * store.
@@ -1139,10 +1250,9 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
                 return status;
 
         /*
-         * Some firmware implementations refuse to boot if there's insufficient
-         * space in the variable store. We account for that by refusing the
-         * write if permitting it would reduce the available space to under
-         * 5KB. This figure was provided by Samsung, so should be safe.
+         * We account for that by refusing the write if permitting it would
+         * reduce the available space to under 5KB. This figure was provided by
+         * Samsung, so should be safe.
          */
         if ((remaining_size - size < EFI_MIN_RESERVE) &&
                 !efi_no_storage_paranoia) {
@@ -1205,8 +1315,27 @@ static int __init parse_efi_cmdline(char *str)
                 str++;
 
         if (!strncmp(str, "old_map", 7))
-                set_bit(EFI_OLD_MEMMAP, &x86_efi_facility);
+                set_bit(EFI_OLD_MEMMAP, &efi.flags);
 
         return 0;
 }
 early_param("efi", parse_efi_cmdline);
+
+void __init efi_apply_memmap_quirks(void)
+{
+        /*
+         * Once setup is done earlier, unmap the EFI memory map on mismatched
+         * firmware/kernel architectures since there is no support for runtime
+         * services.
+         */
+        if (!efi_runtime_supported()) {
+                pr_info("efi: Setup done, disabling due to 32/64-bit mismatch\n");
+                efi_unmap_memmap();
+        }
+
+        /*
+         * UV doesn't support the new EFI pagetable mapping yet.
+         */
+        if (is_uv_system())
+                set_bit(EFI_OLD_MEMMAP, &efi.flags);
+}
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index 0b74cdf7f816..9ee3491e31fb 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -40,7 +40,12 @@
 static unsigned long efi_rt_eflags;
 
 void efi_sync_low_kernel_mappings(void) {}
-void efi_setup_page_tables(void) {}
+void __init efi_dump_pagetable(void) {}
+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+        return 0;
+}
+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages) {}
 
 void __init efi_map_region(efi_memory_desc_t *md)
 {
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 0c2a234fef1e..290d397e1dd9 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -39,6 +39,7 @@
 #include <asm/cacheflush.h>
 #include <asm/fixmap.h>
 #include <asm/realmode.h>
+#include <asm/time.h>
 
 static pgd_t *save_pgd __initdata;
 static unsigned long efi_flags __initdata;
@@ -58,7 +59,8 @@ struct efi_scratch {
         u64 prev_cr3;
         pgd_t *efi_pgt;
         bool use_pgd;
-};
+        u64 phys_stack;
+} __packed;
 
 static void __init early_code_mapping_set_exec(int executable)
 {
@@ -137,12 +139,64 @@ void efi_sync_low_kernel_mappings(void)
                 sizeof(pgd_t) * num_pgds);
 }
 
-void efi_setup_page_tables(void)
+int efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
 {
+        unsigned long text;
+        struct page *page;
+        unsigned npages;
+        pgd_t *pgd;
+
+        if (efi_enabled(EFI_OLD_MEMMAP))
+                return 0;
+
         efi_scratch.efi_pgt = (pgd_t *)(unsigned long)real_mode_header->trampoline_pgd;
+        pgd = __va(efi_scratch.efi_pgt);
 
-        if (!efi_enabled(EFI_OLD_MEMMAP))
-                efi_scratch.use_pgd = true;
+        /*
+         * It can happen that the physical address of new_memmap lands in memory
+         * which is not mapped in the EFI page table. Therefore we need to go
+         * and ident-map those pages containing the map before calling
+         * phys_efi_set_virtual_address_map().
+         */
+        if (kernel_map_pages_in_pgd(pgd, pa_memmap, pa_memmap, num_pages, _PAGE_NX)) {
+                pr_err("Error ident-mapping new memmap (0x%lx)!\n", pa_memmap);
+                return 1;
+        }
+
+        efi_scratch.use_pgd = true;
+
+        /*
+         * When making calls to the firmware everything needs to be 1:1
+         * mapped and addressable with 32-bit pointers. Map the kernel
+         * text and allocate a new stack because we can't rely on the
+         * stack pointer being < 4GB.
+         */
+        if (!IS_ENABLED(CONFIG_EFI_MIXED))
+                return 0;
+
+        page = alloc_page(GFP_KERNEL|__GFP_DMA32);
+        if (!page)
+                panic("Unable to allocate EFI runtime stack < 4GB\n");
+
+        efi_scratch.phys_stack = virt_to_phys(page_address(page));
+        efi_scratch.phys_stack += PAGE_SIZE; /* stack grows down */
+
+        npages = (_end - _text) >> PAGE_SHIFT;
+        text = __pa(_text);
+
+        if (kernel_map_pages_in_pgd(pgd, text >> PAGE_SHIFT, text, npages, 0)) {
+                pr_err("Failed to map kernel text 1:1\n");
+                return 1;
+        }
+
+        return 0;
+}
+
+void efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages)
+{
+        pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+        kernel_unmap_pages_in_pgd(pgd, pa_memmap, num_pages);
 }
 
 static void __init __map_region(efi_memory_desc_t *md, u64 va)
@@ -173,6 +227,16 @@ void __init efi_map_region(efi_memory_desc_t *md)
          */
         __map_region(md, md->phys_addr);
 
+        /*
+         * Enforce the 1:1 mapping as the default virtual address when
+         * booting in EFI mixed mode, because even though we may be
+         * running a 64-bit kernel, the firmware may only be 32-bit.
+         */
+        if (!efi_is_native () && IS_ENABLED(CONFIG_EFI_MIXED)) {
+                md->virt_addr = md->phys_addr;
+                return;
+        }
+
         efi_va -= size;
 
         /* Is PA 2M-aligned? */
@@ -242,3 +306,299 @@ void __init efi_runtime_mkexec(void)
         if (__supported_pte_mask & _PAGE_NX)
                 runtime_code_page_mkexec();
 }
+
+void __init efi_dump_pagetable(void)
+{
+#ifdef CONFIG_EFI_PGT_DUMP
+        pgd_t *pgd = (pgd_t *)__va(real_mode_header->trampoline_pgd);
+
+        ptdump_walk_pgd_level(NULL, pgd);
+#endif
+}
+
+#ifdef CONFIG_EFI_MIXED
+extern efi_status_t efi64_thunk(u32, ...);
+
+#define runtime_service32(func)                                          \
+({                                                                       \
+        u32 table = (u32)(unsigned long)efi.systab;                      \
+        u32 *rt, *___f;                                                  \
+                                                                         \
+        rt = (u32 *)(table + offsetof(efi_system_table_32_t, runtime));  \
+        ___f = (u32 *)(*rt + offsetof(efi_runtime_services_32_t, func)); \
+        *___f;                                                           \
+})
+
+/*
+ * Switch to the EFI page tables early so that we can access the 1:1
+ * runtime services mappings which are not mapped in any other page
+ * tables. This function must be called before runtime_service32().
+ *
+ * Also, disable interrupts because the IDT points to 64-bit handlers,
+ * which aren't going to function correctly when we switch to 32-bit.
+ */
+#define efi_thunk(f, ...)                                               \
+({                                                                      \
+        efi_status_t __s;                                               \
+        unsigned long flags;                                            \
+        u32 func;                                                       \
+                                                                        \
+        efi_sync_low_kernel_mappings();                                 \
+        local_irq_save(flags);                                          \
+                                                                        \
+        efi_scratch.prev_cr3 = read_cr3();                              \
+        write_cr3((unsigned long)efi_scratch.efi_pgt);                  \
+        __flush_tlb_all();                                              \
+                                                                        \
+        func = runtime_service32(f);                                    \
+        __s = efi64_thunk(func, __VA_ARGS__);                   \
+                                                                        \
+        write_cr3(efi_scratch.prev_cr3);                                \
+        __flush_tlb_all();                                              \
+        local_irq_restore(flags);                                       \
+                                                                        \
+        __s;                                                            \
+})
+
+efi_status_t efi_thunk_set_virtual_address_map(
+        void *phys_set_virtual_address_map,
+        unsigned long memory_map_size,
+        unsigned long descriptor_size,
+        u32 descriptor_version,
+        efi_memory_desc_t *virtual_map)
+{
+        efi_status_t status;
+        unsigned long flags;
+        u32 func;
+
+        efi_sync_low_kernel_mappings();
+        local_irq_save(flags);
+
+        efi_scratch.prev_cr3 = read_cr3();
+        write_cr3((unsigned long)efi_scratch.efi_pgt);
+        __flush_tlb_all();
+
+        func = (u32)(unsigned long)phys_set_virtual_address_map;
+        status = efi64_thunk(func, memory_map_size, descriptor_size,
+                             descriptor_version, virtual_map);
+
+        write_cr3(efi_scratch.prev_cr3);
+        __flush_tlb_all();
+        local_irq_restore(flags);
+
+        return status;
+}
+
+static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+        efi_status_t status;
+        u32 phys_tm, phys_tc;
+
+        spin_lock(&rtc_lock);
+
+        phys_tm = virt_to_phys(tm);
+        phys_tc = virt_to_phys(tc);
+
+        status = efi_thunk(get_time, phys_tm, phys_tc);
+
+        spin_unlock(&rtc_lock);
+
+        return status;
+}
+
+static efi_status_t efi_thunk_set_time(efi_time_t *tm)
+{
+        efi_status_t status;
+        u32 phys_tm;
+
+        spin_lock(&rtc_lock);
+
+        phys_tm = virt_to_phys(tm);
+
+        status = efi_thunk(set_time, phys_tm);
+
+        spin_unlock(&rtc_lock);
+
+        return status;
+}
+
+static efi_status_t
+efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
+                          efi_time_t *tm)
+{
+        efi_status_t status;
+        u32 phys_enabled, phys_pending, phys_tm;
+
+        spin_lock(&rtc_lock);
+
+        phys_enabled = virt_to_phys(enabled);
+        phys_pending = virt_to_phys(pending);
+        phys_tm = virt_to_phys(tm);
+
+        status = efi_thunk(get_wakeup_time, phys_enabled,
+                             phys_pending, phys_tm);
+
+        spin_unlock(&rtc_lock);
+
+        return status;
+}
+
+static efi_status_t
+efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+        efi_status_t status;
+        u32 phys_tm;
+
+        spin_lock(&rtc_lock);
+
+        phys_tm = virt_to_phys(tm);
+
+        status = efi_thunk(set_wakeup_time, enabled, phys_tm);
+
+        spin_unlock(&rtc_lock);
+
+        return status;
+}
+
+
+static efi_status_t
+efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
+                       u32 *attr, unsigned long *data_size, void *data)
+{
+        efi_status_t status;
+        u32 phys_name, phys_vendor, phys_attr;
+        u32 phys_data_size, phys_data;
+
+        phys_data_size = virt_to_phys(data_size);
+        phys_vendor = virt_to_phys(vendor);
+        phys_name = virt_to_phys(name);
+        phys_attr = virt_to_phys(attr);
+        phys_data = virt_to_phys(data);
+
+        status = efi_thunk(get_variable, phys_name, phys_vendor,
+                           phys_attr, phys_data_size, phys_data);
+
+        return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
+                       u32 attr, unsigned long data_size, void *data)
+{
+        u32 phys_name, phys_vendor, phys_data;
+        efi_status_t status;
+
+        phys_name = virt_to_phys(name);
+        phys_vendor = virt_to_phys(vendor);
+        phys_data = virt_to_phys(data);
+
+        /* If data_size is > sizeof(u32) we've got problems */
+        status = efi_thunk(set_variable, phys_name, phys_vendor,
+                           attr, data_size, phys_data);
+
+        return status;
+}
+
+static efi_status_t
+efi_thunk_get_next_variable(unsigned long *name_size,
+                            efi_char16_t *name,
+                            efi_guid_t *vendor)
+{
+        efi_status_t status;
+        u32 phys_name_size, phys_name, phys_vendor;
+
+        phys_name_size = virt_to_phys(name_size);
+        phys_vendor = virt_to_phys(vendor);
+        phys_name = virt_to_phys(name);
+
+        status = efi_thunk(get_next_variable, phys_name_size,
+                           phys_name, phys_vendor);
+
+        return status;
+}
+
+static efi_status_t
+efi_thunk_get_next_high_mono_count(u32 *count)
+{
+        efi_status_t status;
+        u32 phys_count;
+
+        phys_count = virt_to_phys(count);
+        status = efi_thunk(get_next_high_mono_count, phys_count);
+
+        return status;
+}
+
+static void
+efi_thunk_reset_system(int reset_type, efi_status_t status,
+                       unsigned long data_size, efi_char16_t *data)
+{
+        u32 phys_data;
+
+        phys_data = virt_to_phys(data);
+
+        efi_thunk(reset_system, reset_type, status, data_size, phys_data);
+}
+
+static efi_status_t
+efi_thunk_update_capsule(efi_capsule_header_t **capsules,
+                         unsigned long count, unsigned long sg_list)
+{
+        /*
+         * To properly support this function we would need to repackage
+         * 'capsules' because the firmware doesn't understand 64-bit
+         * pointers.
+         */
+        return EFI_UNSUPPORTED;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
+                              u64 *remaining_space,
+                              u64 *max_variable_size)
+{
+        efi_status_t status;
+        u32 phys_storage, phys_remaining, phys_max;
+
+        if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+                return EFI_UNSUPPORTED;
+
+        phys_storage = virt_to_phys(storage_space);
+        phys_remaining = virt_to_phys(remaining_space);
+        phys_max = virt_to_phys(max_variable_size);
+
+        status = efi_thunk(query_variable_info, attr, phys_storage,
+                           phys_remaining, phys_max);
+
+        return status;
+}
+
+static efi_status_t
+efi_thunk_query_capsule_caps(efi_capsule_header_t **capsules,
+                             unsigned long count, u64 *max_size,
+                             int *reset_type)
+{
+        /*
+         * To properly support this function we would need to repackage
+         * 'capsules' because the firmware doesn't understand 64-bit
+         * pointers.
+         */
+        return EFI_UNSUPPORTED;
+}
+
+void efi_thunk_runtime_setup(void)
+{
+        efi.get_time = efi_thunk_get_time;
+        efi.set_time = efi_thunk_set_time;
+        efi.get_wakeup_time = efi_thunk_get_wakeup_time;
+        efi.set_wakeup_time = efi_thunk_set_wakeup_time;
+        efi.get_variable = efi_thunk_get_variable;
+        efi.get_next_variable = efi_thunk_get_next_variable;
+        efi.set_variable = efi_thunk_set_variable;
+        efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count;
+        efi.reset_system = efi_thunk_reset_system;
+        efi.query_variable_info = efi_thunk_query_variable_info;
+        efi.update_capsule = efi_thunk_update_capsule;
+        efi.query_capsule_caps = efi_thunk_query_capsule_caps;
+}
+#endif /* CONFIG_EFI_MIXED */
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 88073b140298..e0984ef0374b 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -7,6 +7,10 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/segment.h>
+#include <asm/msr.h>
+#include <asm/processor-flags.h>
+#include <asm/page_types.h>
 
 #define SAVE_XMM                        \
         mov %rsp, %rax;                 \
@@ -164,7 +168,169 @@ ENTRY(efi_call6)
         ret
 ENDPROC(efi_call6)
 
+#ifdef CONFIG_EFI_MIXED
+
+/*
+ * We run this function from the 1:1 mapping.
+ *
+ * This function must be invoked with a 1:1 mapped stack.
+ */
+ENTRY(__efi64_thunk)
+        movl    %ds, %eax
+        push    %rax
+        movl    %es, %eax
+        push    %rax
+        movl    %ss, %eax
+        push    %rax
+
+        subq    $32, %rsp
+        movl    %esi, 0x0(%rsp)
+        movl    %edx, 0x4(%rsp)
+        movl    %ecx, 0x8(%rsp)
+        movq    %r8, %rsi
+        movl    %esi, 0xc(%rsp)
+        movq    %r9, %rsi
+        movl    %esi,  0x10(%rsp)
+
+        sgdt    save_gdt(%rip)
+
+        leaq    1f(%rip), %rbx
+        movq    %rbx, func_rt_ptr(%rip)
+
+        /* Switch to gdt with 32-bit segments */
+        movl    64(%rsp), %eax
+        lgdt    (%rax)
+
+        leaq    efi_enter32(%rip), %rax
+        pushq   $__KERNEL_CS
+        pushq   %rax
+        lretq
+
+1:      addq    $32, %rsp
+
+        lgdt    save_gdt(%rip)
+
+        pop     %rbx
+        movl    %ebx, %ss
+        pop     %rbx
+        movl    %ebx, %es
+        pop     %rbx
+        movl    %ebx, %ds
+
+        /*
+         * Convert 32-bit status code into 64-bit.
+         */
+        test    %rax, %rax
+        jz      1f
+        movl    %eax, %ecx
+        andl    $0x0fffffff, %ecx
+        andl    $0xf0000000, %eax
+        shl     $32, %rax
+        or      %rcx, %rax
+1:
+        ret
+ENDPROC(__efi64_thunk)
+
+ENTRY(efi_exit32)
+        movq    func_rt_ptr(%rip), %rax
+        push    %rax
+        mov     %rdi, %rax
+        ret
+ENDPROC(efi_exit32)
+
+        .code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+        movl    $__KERNEL_DS, %eax
+        movl    %eax, %ds
+        movl    %eax, %es
+        movl    %eax, %ss
+
+        /* Reload pgtables */
+        movl    %cr3, %eax
+        movl    %eax, %cr3
+
+        /* Disable paging */
+        movl    %cr0, %eax
+        btrl    $X86_CR0_PG_BIT, %eax
+        movl    %eax, %cr0
+
+        /* Disable long mode via EFER */
+        movl    $MSR_EFER, %ecx
+        rdmsr
+        btrl    $_EFER_LME, %eax
+        wrmsr
+
+        call    *%edi
+
+        /* We must preserve return value */
+        movl    %eax, %edi
+
+        /*
+         * Some firmware will return with interrupts enabled. Be sure to
+         * disable them before we switch GDTs.
+         */
+        cli
+
+        movl    68(%esp), %eax
+        movl    %eax, 2(%eax)
+        lgdtl   (%eax)
+
+        movl    %cr4, %eax
+        btsl    $(X86_CR4_PAE_BIT), %eax
+        movl    %eax, %cr4
+
+        movl    %cr3, %eax
+        movl    %eax, %cr3
+
+        movl    $MSR_EFER, %ecx
+        rdmsr
+        btsl    $_EFER_LME, %eax
+        wrmsr
+
+        xorl    %eax, %eax
+        lldt    %ax
+
+        movl    72(%esp), %eax
+        pushl   $__KERNEL_CS
+        pushl   %eax
+
+        /* Enable paging */
+        movl    %cr0, %eax
+        btsl    $X86_CR0_PG_BIT, %eax
+        movl    %eax, %cr0
+        lret
+ENDPROC(efi_enter32)
+
+        .data
+        .balign 8
+        .global efi32_boot_gdt
+efi32_boot_gdt: .word   0
+                .quad   0
+
+save_gdt:       .word   0
+                .quad   0
+func_rt_ptr:    .quad   0
+
+        .global efi_gdt64
+efi_gdt64:
+        .word   efi_gdt64_end - efi_gdt64
+        .long   0                       /* Filled out by user */
+        .word   0
+        .quad   0x0000000000000000      /* NULL descriptor */
+        .quad   0x00af9a000000ffff      /* __KERNEL_CS */
+        .quad   0x00cf92000000ffff      /* __KERNEL_DS */
+        .quad   0x0080890000000000      /* TS descriptor */
+        .quad   0x0000000000000000      /* TS continued */
+efi_gdt64_end:
+#endif /* CONFIG_EFI_MIXED */
+
         .data
 ENTRY(efi_scratch)
         .fill 3,8,0
         .byte 0
+        .quad 0
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
new file mode 100644
index 000000000000..8806fa73e6e6
--- /dev/null
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -0,0 +1,65 @@
+/*
+ * Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ */
+
+#include <linux/linkage.h>
+#include <asm/page_types.h>
+
+        .text
+        .code64
+ENTRY(efi64_thunk)
+        push    %rbp
+        push    %rbx
+
+        /*
+         * Switch to 1:1 mapped 32-bit stack pointer.
+         */
+        movq    %rsp, efi_saved_sp(%rip)
+        movq    efi_scratch+25(%rip), %rsp
+
+        /*
+         * Calculate the physical address of the kernel text.
+         */
+        movq    $__START_KERNEL_map, %rax
+        subq    phys_base(%rip), %rax
+
+        /*
+         * Push some physical addresses onto the stack. This is easier
+         * to do now in a code64 section while the assembler can address
+         * 64-bit values. Note that all the addresses on the stack are
+         * 32-bit.
+         */
+        subq    $16, %rsp
+        leaq    efi_exit32(%rip), %rbx
+        subq    %rax, %rbx
+        movl    %ebx, 8(%rsp)
+        leaq    efi_gdt64(%rip), %rbx
+        subq    %rax, %rbx
+        movl    %ebx, 2(%ebx)
+        movl    %ebx, 4(%rsp)
+        leaq    efi_gdt32(%rip), %rbx
+        subq    %rax, %rbx
+        movl    %ebx, 2(%ebx)
+        movl    %ebx, (%rsp)
+
+        leaq    __efi64_thunk(%rip), %rbx
+        subq    %rax, %rbx
+        call    *%rbx
+
+        movq    efi_saved_sp(%rip), %rsp
+        pop     %rbx
+        pop     %rbp
+        retq
+ENDPROC(efi64_thunk)
+
+        .data
+efi_gdt32:
+        .word   efi_gdt32_end - efi_gdt32
+        .long   0                       /* Filled out above */
+        .word   0
+        .quad   0x0000000000000000      /* NULL descriptor */
+        .quad   0x00cf9a000000ffff      /* __KERNEL_CS */
+        .quad   0x00cf93000000ffff      /* __KERNEL_DS */
+efi_gdt32_end:
+
+efi_saved_sp:           .quad 0
diff --git a/arch/x86/platform/ts5500/ts5500.c b/arch/x86/platform/ts5500/ts5500.c
index 39febb214e8c..9471b9456f25 100644
--- a/arch/x86/platform/ts5500/ts5500.c
+++ b/arch/x86/platform/ts5500/ts5500.c
@@ -88,7 +88,7 @@ struct ts5500_sbc {
 static const struct {
         const char * const string;
         const ssize_t offset;
-} ts5500_signatures[] __initdata = {
+} ts5500_signatures[] __initconst = {
         { "TS-5x00 AMD Elan", 0xb14 },
 };
 
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
index 7d01b8c56c00..cc04e67bfd05 100644
--- a/arch/x86/um/asm/barrier.h
+++ b/arch/x86/um/asm/barrier.h
@@ -40,11 +40,7 @@
 #define smp_rmb()       barrier()
 #endif /* CONFIG_X86_PPRO_FENCE */
 
-#ifdef CONFIG_X86_OOSTORE
-#define smp_wmb()       wmb()
-#else /* CONFIG_X86_OOSTORE */
 #define smp_wmb()       barrier()
-#endif /* CONFIG_X86_OOSTORE */
 
 #define smp_read_barrier_depends()      read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index fd14be1d1472..9206ac7961a5 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -2,6 +2,8 @@
 # Building vDSO images for x86.
 #
 
+KBUILD_CFLAGS += $(DISABLE_LTO)
+
 VDSO64-$(CONFIG_X86_64)         := y
 VDSOX32-$(CONFIG_X86_X32_ABI)   := y
 VDSO32-$(CONFIG_X86_32)         := y
@@ -35,7 +37,8 @@ export CPPFLAGS_vdso.lds += -P -C
 
 VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
                         -Wl,--no-undefined \
-                        -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
+                        -Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
+                        $(DISABLE_LTO)
 
 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
 
@@ -127,7 +130,7 @@ vdso32.so-$(VDSO32-y)		+= sysenter
 vdso32-images                   = $(vdso32.so-y:%=vdso32-%.so)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
 
 # This makes sure the $(obj) subdirectory exists even though vdso32/
 # is not a kbuild sub-make subdirectory.
@@ -181,7 +184,8 @@ quiet_cmd_vdso = VDSO    $@
                        -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
                  sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
+VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
+                $(LTO_CFLAGS)
 GCOV_PROFILE := n
 
 #
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 256282e7888b..2423ef04ffea 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -365,7 +365,7 @@ void xen_ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
 /* Assume pteval_t is equivalent to all the other *val_t types. */
 static pteval_t pte_mfn_to_pfn(pteval_t val)
 {
-        if (pteval_present(val)) {
+        if (val & _PAGE_PRESENT) {
                 unsigned long mfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
                 unsigned long pfn = mfn_to_pfn(mfn);
 
@@ -381,7 +381,7 @@ static pteval_t pte_mfn_to_pfn(pteval_t val)
 
 static pteval_t pte_pfn_to_mfn(pteval_t val)
 {
-        if (pteval_present(val)) {
+        if (val & _PAGE_PRESENT) {
                 unsigned long pfn = (val & PTE_PFN_MASK) >> PAGE_SHIFT;
                 pteval_t flags = val & PTE_FLAGS_MASK;
                 unsigned long mfn;
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 581521c843a5..4d3acc34a998 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -183,7 +183,7 @@ __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
 
         local_irq_save(flags);
 
-        kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
+        kstat_incr_irq_this_cpu(irq);
 out:
         cpumask_clear_cpu(cpu, &waiting_cpus);
         w->lock = NULL;
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index ba56e11cbf77..c87ae7c6e5f9 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -20,6 +20,7 @@ config XTENSA
         select HAVE_FUNCTION_TRACER
         select HAVE_IRQ_TIME_ACCOUNTING
         select HAVE_PERF_EVENTS
+        select COMMON_CLK
         help
           Xtensa processors are 32-bit RISC machines designed by Tensilica
           primarily for embedded systems.  These processors are both
@@ -80,7 +81,6 @@ choice
 config XTENSA_VARIANT_FSF
         bool "fsf - default (not generic) configuration"
         select MMU
-        select HAVE_XTENSA_GPIO32
 
 config XTENSA_VARIANT_DC232B
         bool "dc232b - Diamond 232L Standard Core Rev.B (LE)"
@@ -135,7 +135,6 @@ config HAVE_SMP
 config SMP
         bool "Enable Symmetric multi-processing support"
         depends on HAVE_SMP
-        select USE_GENERIC_SMP_HELPERS
         select GENERIC_SMP_IDLE_THREAD
         help
           Enabled SMP Software; allows more than one CPU/CORE
diff --git a/arch/xtensa/boot/dts/xtfpga.dtsi b/arch/xtensa/boot/dts/xtfpga.dtsi
index 46b4f5eab421..e7370b11348e 100644
--- a/arch/xtensa/boot/dts/xtfpga.dtsi
+++ b/arch/xtensa/boot/dts/xtfpga.dtsi
@@ -35,6 +35,13 @@
                 interrupt-controller;
         };
 
+        clocks {
+                osc: main-oscillator {
+                        #clock-cells = <0>;
+                        compatible = "fixed-clock";
+                };
+        };
+
         serial0: serial@fd050020 {
                 device_type = "serial";
                 compatible = "ns16550a";
@@ -42,9 +49,7 @@
                 reg = <0xfd050020 0x20>;
                 reg-shift = <2>;
                 interrupts = <0 1>; /* external irq 0 */
-                /* Filled in by platform_setup from FPGA register
-                 * clock-frequency = <100000000>;
-                 */
+                clocks = <&osc>;
         };
 
         enet0: ethoc@fd030000 {
@@ -52,5 +57,6 @@
                 reg = <0xfd030000 0x4000 0xfd800000 0x4000>;
                 interrupts = <1 1>; /* external irq 1 */
                 local-mac-address = [00 50 c2 13 6f 00];
+                clocks = <&osc>;
         };
 };
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 0a337e4a8370..c3d20ba6eb86 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += errno.h
 generic-y += exec.h
 generic-y += fcntl.h
 generic-y += hardirq.h
+generic-y += hash.h
 generic-y += ioctl.h
 generic-y += irq_regs.h
 generic-y += kdebug.h
@@ -17,7 +18,9 @@ generic-y += kvm_para.h
 generic-y += linkage.h
 generic-y += local.h
 generic-y += local64.h
+generic-y += mcs_spinlock.h
 generic-y += percpu.h
+generic-y += preempt.h
 generic-y += resource.h
 generic-y += scatterlist.h
 generic-y += sections.h
@@ -27,5 +30,3 @@ generic-y += termios.h
 generic-y += topology.h
 generic-y += trace_clock.h
 generic-y += xor.h
-generic-y += preempt.h
-generic-y += hash.h
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 2a042d430c25..74944207167e 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -25,7 +25,7 @@
 
 #ifdef CONFIG_MMU
 
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 extern unsigned long xtensa_kio_paddr;
 
 static inline unsigned long xtensa_get_kio_paddr(void)
diff --git a/arch/xtensa/include/asm/traps.h b/arch/xtensa/include/asm/traps.h
index 8c194f6af45e..677bfcf4ee5d 100644
--- a/arch/xtensa/include/asm/traps.h
+++ b/arch/xtensa/include/asm/traps.h
@@ -23,25 +23,37 @@ void secondary_trap_init(void);
 
 static inline void spill_registers(void)
 {
-
+#if XCHAL_NUM_AREGS > 16
         __asm__ __volatile__ (
-                "movi   a14, "__stringify((1 << PS_EXCM_BIT) | LOCKLEVEL)"\n\t"
-                "mov    a12, a0\n\t"
-                "rsr    a13, sar\n\t"
-                "xsr    a14, ps\n\t"
-                "movi   a0, _spill_registers\n\t"
-                "rsync\n\t"
-                "callx0 a0\n\t"
-                "mov    a0, a12\n\t"
-                "wsr    a13, sar\n\t"
-                "wsr    a14, ps\n\t"
-                : :
-#if defined(CONFIG_FRAME_POINTER)
-                : "a2", "a3", "a4",       "a11", "a12", "a13", "a14", "a15",
+                "       call12  1f\n"
+                "       _j      2f\n"
+                "       retw\n"
+                "       .align  4\n"
+                "1:\n"
+                "       _entry  a1, 48\n"
+                "       addi    a12, a0, 3\n"
+#if XCHAL_NUM_AREGS > 32
+                "       .rept   (" __stringify(XCHAL_NUM_AREGS) " - 32) / 12\n"
+                "       _entry  a1, 48\n"
+                "       mov     a12, a0\n"
+                "       .endr\n"
+#endif
+                "       _entry  a1, 48\n"
+#if XCHAL_NUM_AREGS % 12 == 0
+                "       mov     a8, a8\n"
+#elif XCHAL_NUM_AREGS % 12 == 4
+                "       mov     a12, a12\n"
+#elif XCHAL_NUM_AREGS % 12 == 8
+                "       mov     a4, a4\n"
+#endif
+                "       retw\n"
+                "2:\n"
+                : : : "a12", "a13", "memory");
 #else
-                : "a2", "a3", "a4", "a7", "a11", "a12", "a13", "a14", "a15",
+        __asm__ __volatile__ (
+                "       mov     a12, a12\n"
+                : : : "memory");
 #endif
-                  "memory");
 }
 
 #endif /* _XTENSA_TRAPS_H */
diff --git a/arch/xtensa/include/asm/vectors.h b/arch/xtensa/include/asm/vectors.h
index 5791b45d5a5d..f74ddfbb92ef 100644
--- a/arch/xtensa/include/asm/vectors.h
+++ b/arch/xtensa/include/asm/vectors.h
@@ -25,7 +25,7 @@
 #define XCHAL_KIO_DEFAULT_PADDR         0xf0000000
 #define XCHAL_KIO_SIZE                  0x10000000
 
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
 #define XCHAL_KIO_PADDR                 xtensa_get_kio_paddr()
 #else
 #define XCHAL_KIO_PADDR                 XCHAL_KIO_DEFAULT_PADDR
diff --git a/arch/xtensa/include/uapi/asm/unistd.h b/arch/xtensa/include/uapi/asm/unistd.h
index 51940fec6990..b9395529f02d 100644
--- a/arch/xtensa/include/uapi/asm/unistd.h
+++ b/arch/xtensa/include/uapi/asm/unistd.h
@@ -734,7 +734,12 @@ __SYSCALL(332, sys_finit_module, 3)
 #define __NR_accept4                            333
 __SYSCALL(333, sys_accept4, 4)
 
-#define __NR_syscall_count                      334
+#define __NR_sched_setattr                      334
+__SYSCALL(334, sys_sched_setattr, 2)
+#define __NR_sched_getattr                      335
+__SYSCALL(335, sys_sched_getattr, 3)
+
+#define __NR_syscall_count                      336
 
 /*
  * sysxtensa syscall handler
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index 21dbe6bdb8ed..ef7f4990722b 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1081,196 +1081,53 @@ ENTRY(fast_syscall_spill_registers)
 
         rsr     a0, sar
         s32i    a3, a2, PT_AREG3
-        s32i    a4, a2, PT_AREG4
-        s32i    a0, a2, PT_AREG5        # store SAR to PT_AREG5
+        s32i    a0, a2, PT_SAR
 
-        /* The spill routine might clobber a7, a11, and a15. */
+        /* The spill routine might clobber a4, a7, a8, a11, a12, and a15. */
 
+        s32i    a4, a2, PT_AREG4
         s32i    a7, a2, PT_AREG7
+        s32i    a8, a2, PT_AREG8
         s32i    a11, a2, PT_AREG11
+        s32i    a12, a2, PT_AREG12
         s32i    a15, a2, PT_AREG15
 
-        call0   _spill_registers        # destroys a3, a4, and SAR
-
-        /* Advance PC, restore registers and SAR, and return from exception. */
-
-        l32i    a3, a2, PT_AREG5
-        l32i    a4, a2, PT_AREG4
-        l32i    a0, a2, PT_AREG0
-        wsr     a3, sar
-        l32i    a3, a2, PT_AREG3
-
-        /* Restore clobbered registers. */
-
-        l32i    a7, a2, PT_AREG7
-        l32i    a11, a2, PT_AREG11
-        l32i    a15, a2, PT_AREG15
-
-        movi    a2, 0
-        rfe
-
-ENDPROC(fast_syscall_spill_registers)
-
-/* Fixup handler.
- *
- * We get here if the spill routine causes an exception, e.g. tlb miss.
- * We basically restore WINDOWBASE and WINDOWSTART to the condition when
- * we entered the spill routine and jump to the user exception handler.
- *
- * a0: value of depc, original value in depc
- * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
- * a3: exctable, original value in excsave1
- */
-
-ENTRY(fast_syscall_spill_registers_fixup)
-
-        rsr     a2, windowbase  # get current windowbase (a2 is saved)
-        xsr     a0, depc        # restore depc and a0
-        ssl     a2              # set shift (32 - WB)
-
-        /* We need to make sure the current registers (a0-a3) are preserved.
-         * To do this, we simply set the bit for the current window frame
-         * in WS, so that the exception handlers save them to the task stack.
-         */
-
-        xsr     a3, excsave1    # get spill-mask
-        slli    a3, a3, 1       # shift left by one
-
-        slli    a2, a3, 32-WSBITS
-        src     a2, a3, a2      # a2 = xxwww1yyxxxwww1yy......
-        wsr     a2, windowstart # set corrected windowstart
-
-        srli    a3, a3, 1
-        rsr     a2, excsave1
-        l32i    a2, a2, EXC_TABLE_DOUBLE_SAVE   # restore a2
-        xsr     a2, excsave1
-        s32i    a3, a2, EXC_TABLE_DOUBLE_SAVE   # save a3
-        l32i    a3, a2, EXC_TABLE_PARAM # original WB (in user task)
-        xsr     a2, excsave1
-
-        /* Return to the original (user task) WINDOWBASE.
-         * We leave the following frame behind:
-         * a0, a1, a2   same
-         * a3:          trashed (saved in EXC_TABLE_DOUBLE_SAVE)
-         * depc:        depc (we have to return to that address)
-         * excsave_1:   exctable
-         */
-
-        wsr     a3, windowbase
-        rsync
-
-        /* We are now in the original frame when we entered _spill_registers:
-         *  a0: return address
-         *  a1: used, stack pointer
-         *  a2: kernel stack pointer
-         *  a3: available
-         *  depc: exception address
-         *  excsave: exctable
-         * Note: This frame might be the same as above.
-         */
-
-        /* Setup stack pointer. */
-
-        addi    a2, a2, -PT_USER_SIZE
-        s32i    a0, a2, PT_AREG0
-
-        /* Make sure we return to this fixup handler. */
-
-        movi    a3, fast_syscall_spill_registers_fixup_return
-        s32i    a3, a2, PT_DEPC         # setup depc
-
-        /* Jump to the exception handler. */
-
-        rsr     a3, excsave1
-        rsr     a0, exccause
-        addx4   a0, a0, a3                      # find entry in table
-        l32i    a0, a0, EXC_TABLE_FAST_USER     # load handler
-        l32i    a3, a3, EXC_TABLE_DOUBLE_SAVE
-        jx      a0
-
-ENDPROC(fast_syscall_spill_registers_fixup)
-
-ENTRY(fast_syscall_spill_registers_fixup_return)
-
-        /* When we return here, all registers have been restored (a2: DEPC) */
-
-        wsr     a2, depc                # exception address
-
-        /* Restore fixup handler. */
-
-        rsr     a2, excsave1
-        s32i    a3, a2, EXC_TABLE_DOUBLE_SAVE
-        movi    a3, fast_syscall_spill_registers_fixup
-        s32i    a3, a2, EXC_TABLE_FIXUP
-        rsr     a3, windowbase
-        s32i    a3, a2, EXC_TABLE_PARAM
-        l32i    a2, a2, EXC_TABLE_KSTK
-
-        /* Load WB at the time the exception occurred. */
-
-        rsr     a3, sar                 # WB is still in SAR
-        neg     a3, a3
-        wsr     a3, windowbase
-        rsync
-
-        rsr     a3, excsave1
-        l32i    a3, a3, EXC_TABLE_DOUBLE_SAVE
-
-        rfde
-
-ENDPROC(fast_syscall_spill_registers_fixup_return)
-
-/*
- * spill all registers.
- *
- * This is not a real function. The following conditions must be met:
- *
- *  - must be called with call0.
- *  - uses a3, a4 and SAR.
- *  - the last 'valid' register of each frame are clobbered.
- *  - the caller must have registered a fixup handler
- *    (or be inside a critical section)
- *  - PS_EXCM must be set (PS_WOE cleared?)
- */
-
-ENTRY(_spill_registers)
-
         /*
          * Rotate ws so that the current windowbase is at bit 0.
          * Assume ws = xxxwww1yy (www1 current window frame).
          * Rotate ws right so that a4 = yyxxxwww1.
          */
 
-        rsr     a4, windowbase
+        rsr     a0, windowbase
         rsr     a3, windowstart         # a3 = xxxwww1yy
-        ssr     a4                      # holds WB
-        slli    a4, a3, WSBITS
-        or      a3, a3, a4              # a3 = xxxwww1yyxxxwww1yy
+        ssr     a0                      # holds WB
+        slli    a0, a3, WSBITS
+        or      a3, a3, a0              # a3 = xxxwww1yyxxxwww1yy
         srl     a3, a3                  # a3 = 00xxxwww1yyxxxwww1
 
         /* We are done if there are no more than the current register frame. */
 
         extui   a3, a3, 1, WSBITS-1     # a3 = 0yyxxxwww
-        movi    a4, (1 << (WSBITS-1))
+        movi    a0, (1 << (WSBITS-1))
         _beqz   a3, .Lnospill           # only one active frame? jump
 
         /* We want 1 at the top, so that we return to the current windowbase */
 
-        or      a3, a3, a4              # 1yyxxxwww
+        or      a3, a3, a0              # 1yyxxxwww
 
         /* Skip empty frames - get 'oldest' WINDOWSTART-bit. */
 
         wsr     a3, windowstart         # save shifted windowstart
-        neg     a4, a3
-        and     a3, a4, a3              # first bit set from right: 000010000
+        neg     a0, a3
+        and     a3, a0, a3              # first bit set from right: 000010000
 
-        ffs_ws  a4, a3                  # a4: shifts to skip empty frames
+        ffs_ws  a0, a3                  # a0: shifts to skip empty frames
         movi    a3, WSBITS
-        sub     a4, a3, a4              # WSBITS-a4:number of 0-bits from right
-        ssr     a4                      # save in SAR for later.
+        sub     a0, a3, a0              # WSBITS-a0:number of 0-bits from right
+        ssr     a0                      # save in SAR for later.
 
         rsr     a3, windowbase
-        add     a3, a3, a4
+        add     a3, a3, a0
         wsr     a3, windowbase
         rsync
 
@@ -1285,22 +1142,6 @@ ENTRY(_spill_registers)
          * we have to save 4,8. or 12 registers.
          */
 
-        _bbsi.l a3, 1, .Lc4
-        _bbsi.l a3, 2, .Lc8
-
-        /* Special case: we have a call12-frame starting at a4. */
-
-        _bbci.l a3, 3, .Lc12    # bit 3 shouldn't be zero! (Jump to Lc12 first)
-
-        s32e    a4, a1, -16     # a1 is valid with an empty spill area
-        l32e    a4, a5, -12
-        s32e    a8, a4, -48
-        mov     a8, a4
-        l32e    a4, a1, -16
-        j       .Lc12c
-
-.Lnospill:
-        ret
 
 .Lloop: _bbsi.l a3, 1, .Lc4
         _bbci.l a3, 2, .Lc12
@@ -1314,20 +1155,10 @@ ENTRY(_spill_registers)
         s32e    a9, a4, -28
         s32e    a10, a4, -24
         s32e    a11, a4, -20
-
         srli    a11, a3, 2              # shift windowbase by 2
         rotw    2
         _bnei   a3, 1, .Lloop
-
-.Lexit: /* Done. Do the final rotation, set WS, and return. */
-
-        rotw    1
-        rsr     a3, windowbase
-        ssl     a3
-        movi    a3, 1
-        sll     a3, a3
-        wsr     a3, windowstart
-        ret
+        j       .Lexit
 
 .Lc4:   s32e    a4, a9, -16
         s32e    a5, a9, -12
@@ -1343,11 +1174,11 @@ ENTRY(_spill_registers)
 
         /* 12-register frame (call12) */
 
-        l32e    a2, a5, -12
-        s32e    a8, a2, -48
-        mov     a8, a2
+        l32e    a0, a5, -12
+        s32e    a8, a0, -48
+        mov     a8, a0
 
-.Lc12c: s32e    a9, a8, -44
+        s32e    a9, a8, -44
         s32e    a10, a8, -40
         s32e    a11, a8, -36
         s32e    a12, a8, -32
@@ -1367,30 +1198,54 @@ ENTRY(_spill_registers)
          */
 
         rotw    1
-        mov     a5, a13
+        mov     a4, a13
         rotw    -1
 
-        s32e    a4, a9, -16
-        s32e    a5, a9, -12
-        s32e    a6, a9, -8
-        s32e    a7, a9, -4
+        s32e    a4, a8, -16
+        s32e    a5, a8, -12
+        s32e    a6, a8, -8
+        s32e    a7, a8, -4
 
         rotw    3
 
         _beqi   a3, 1, .Lexit
         j       .Lloop
 
-.Linvalid_mask:
+.Lexit:
 
-        /* We get here because of an unrecoverable error in the window
-         * registers. If we are in user space, we kill the application,
-         * however, this condition is unrecoverable in kernel space.
-         */
+        /* Done. Do the final rotation and set WS */
+
+        rotw    1
+        rsr     a3, windowbase
+        ssl     a3
+        movi    a3, 1
+        sll     a3, a3
+        wsr     a3, windowstart
+.Lnospill:
+
+        /* Advance PC, restore registers and SAR, and return from exception. */
+
+        l32i    a3, a2, PT_SAR
+        l32i    a0, a2, PT_AREG0
+        wsr     a3, sar
+        l32i    a3, a2, PT_AREG3
 
-        rsr     a0, ps
-        _bbci.l a0, PS_UM_BIT, 1f
+        /* Restore clobbered registers. */
 
-        /* User space: Setup a dummy frame and kill application.
+        l32i    a4, a2, PT_AREG4
+        l32i    a7, a2, PT_AREG7
+        l32i    a8, a2, PT_AREG8
+        l32i    a11, a2, PT_AREG11
+        l32i    a12, a2, PT_AREG12
+        l32i    a15, a2, PT_AREG15
+
+        movi    a2, 0
+        rfe
+
+.Linvalid_mask:
+
+        /* We get here because of an unrecoverable error in the window
+         * registers, so set up a dummy frame and kill the user application.
          * Note: We assume EXC_TABLE_KSTK contains a valid stack pointer.
          */
 
@@ -1414,14 +1269,136 @@ ENTRY(_spill_registers)
         movi    a4, do_exit
         callx4  a4
 
-1:      /* Kernel space: PANIC! */
+        /* shouldn't return, so panic */
 
         wsr     a0, excsave1
         movi    a0, unrecoverable_exception
         callx0  a0              # should not return
 1:      j       1b
 
-ENDPROC(_spill_registers)
+
+ENDPROC(fast_syscall_spill_registers)
+
+/* Fixup handler.
+ *
+ * We get here if the spill routine causes an exception, e.g. tlb miss.
+ * We basically restore WINDOWBASE and WINDOWSTART to the condition when
+ * we entered the spill routine and jump to the user exception handler.
+ *
+ * Note that we only need to restore the bits in windowstart that have not
+ * been spilled yet by the _spill_register routine. Luckily, a3 contains a
+ * rotated windowstart with only those bits set for frames that haven't been
+ * spilled yet. Because a3 is rotated such that bit 0 represents the register
+ * frame for the current windowbase - 1, we need to rotate a3 left by the
+ * value of the current windowbase + 1 and move it to windowstart.
+ *
+ * a0: value of depc, original value in depc
+ * a2: trashed, original value in EXC_TABLE_DOUBLE_SAVE
+ * a3: exctable, original value in excsave1
+ */
+
+ENTRY(fast_syscall_spill_registers_fixup)
+
+        rsr     a2, windowbase  # get current windowbase (a2 is saved)
+        xsr     a0, depc        # restore depc and a0
+        ssl     a2              # set shift (32 - WB)
+
+        /* We need to make sure the current registers (a0-a3) are preserved.
+         * To do this, we simply set the bit for the current window frame
+         * in WS, so that the exception handlers save them to the task stack.
+         *
+         * Note: we use a3 to set the windowbase, so we take a special care
+         * of it, saving it in the original _spill_registers frame across
+         * the exception handler call.
+         */
+
+        xsr     a3, excsave1    # get spill-mask
+        slli    a3, a3, 1       # shift left by one
+        addi    a3, a3, 1       # set the bit for the current window frame
+
+        slli    a2, a3, 32-WSBITS
+        src     a2, a3, a2      # a2 = xxwww1yyxxxwww1yy......
+        wsr     a2, windowstart # set corrected windowstart
+
+        srli    a3, a3, 1
+        rsr     a2, excsave1
+        l32i    a2, a2, EXC_TABLE_DOUBLE_SAVE   # restore a2
+        xsr     a2, excsave1
+        s32i    a3, a2, EXC_TABLE_DOUBLE_SAVE   # save a3
+        l32i    a3, a2, EXC_TABLE_PARAM # original WB (in user task)
+        xsr     a2, excsave1
+
+        /* Return to the original (user task) WINDOWBASE.
+         * We leave the following frame behind:
+         * a0, a1, a2   same
+         * a3:          trashed (saved in EXC_TABLE_DOUBLE_SAVE)
+         * depc:        depc (we have to return to that address)
+         * excsave_1:   exctable
+         */
+
+        wsr     a3, windowbase
+        rsync
+
+        /* We are now in the original frame when we entered _spill_registers:
+         *  a0: return address
+         *  a1: used, stack pointer
+         *  a2: kernel stack pointer
+         *  a3: available
+         *  depc: exception address
+         *  excsave: exctable
+         * Note: This frame might be the same as above.
+         */
+
+        /* Setup stack pointer. */
+
+        addi    a2, a2, -PT_USER_SIZE
+        s32i    a0, a2, PT_AREG0
+
+        /* Make sure we return to this fixup handler. */
+
+        movi    a3, fast_syscall_spill_registers_fixup_return
+        s32i    a3, a2, PT_DEPC         # setup depc
+
+        /* Jump to the exception handler. */
+
+        rsr     a3, excsave1
+        rsr     a0, exccause
+        addx4   a0, a0, a3                      # find entry in table
+        l32i    a0, a0, EXC_TABLE_FAST_USER     # load handler
+        l32i    a3, a3, EXC_TABLE_DOUBLE_SAVE
+        jx      a0
+
+ENDPROC(fast_syscall_spill_registers_fixup)
+
+ENTRY(fast_syscall_spill_registers_fixup_return)
+
+        /* When we return here, all registers have been restored (a2: DEPC) */
+
+        wsr     a2, depc                # exception address
+
+        /* Restore fixup handler. */
+
+        rsr     a2, excsave1
+        s32i    a3, a2, EXC_TABLE_DOUBLE_SAVE
+        movi    a3, fast_syscall_spill_registers_fixup
+        s32i    a3, a2, EXC_TABLE_FIXUP
+        rsr     a3, windowbase
+        s32i    a3, a2, EXC_TABLE_PARAM
+        l32i    a2, a2, EXC_TABLE_KSTK
+
+        /* Load WB at the time the exception occurred. */
+
+        rsr     a3, sar                 # WB is still in SAR
+        neg     a3, a3
+        wsr     a3, windowbase
+        rsync
+
+        rsr     a3, excsave1
+        l32i    a3, a3, EXC_TABLE_DOUBLE_SAVE
+
+        rfde
+
+ENDPROC(fast_syscall_spill_registers_fixup_return)
 
 #ifdef CONFIG_MMU
 /*
@@ -1794,6 +1771,43 @@ ENTRY(system_call)
 
 ENDPROC(system_call)
 
+/*
+ * Spill live registers on the kernel stack macro.
+ *
+ * Entry condition: ps.woe is set, ps.excm is cleared
+ * Exit condition: windowstart has single bit set
+ * May clobber: a12, a13
+ */
+        .macro  spill_registers_kernel
+
+#if XCHAL_NUM_AREGS > 16
+        call12  1f
+        _j      2f
+        retw
+        .align  4
+1:
+        _entry  a1, 48
+        addi    a12, a0, 3
+#if XCHAL_NUM_AREGS > 32
+        .rept   (XCHAL_NUM_AREGS - 32) / 12
+        _entry  a1, 48
+        mov     a12, a0
+        .endr
+#endif
+        _entry  a1, 48
+#if XCHAL_NUM_AREGS % 12 == 0
+        mov     a8, a8
+#elif XCHAL_NUM_AREGS % 12 == 4
+        mov     a12, a12
+#elif XCHAL_NUM_AREGS % 12 == 8
+        mov     a4, a4
+#endif
+        retw
+2:
+#else
+        mov     a12, a12
+#endif
+        .endm
 
 /*
  * Task switch.
@@ -1806,21 +1820,20 @@ ENTRY(_switch_to)
 
         entry   a1, 16
 
-        mov     a12, a2                 # preserve 'prev' (a2)
-        mov     a13, a3                 # and 'next' (a3)
+        mov     a10, a2                 # preserve 'prev' (a2)
+        mov     a11, a3                 # and 'next' (a3)
 
         l32i    a4, a2, TASK_THREAD_INFO
         l32i    a5, a3, TASK_THREAD_INFO
 
-        save_xtregs_user a4 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+        save_xtregs_user a4 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
-        s32i    a0, a12, THREAD_RA      # save return address
-        s32i    a1, a12, THREAD_SP      # save stack pointer
+        s32i    a0, a10, THREAD_RA      # save return address
+        s32i    a1, a10, THREAD_SP      # save stack pointer
 
         /* Disable ints while we manipulate the stack pointer. */
 
-        movi    a14, (1 << PS_EXCM_BIT) | LOCKLEVEL
-        xsr     a14, ps
+        rsil    a14, LOCKLEVEL
         rsr     a3, excsave1
         rsync
         s32i    a3, a3, EXC_TABLE_FIXUP /* enter critical section */
@@ -1835,7 +1848,7 @@ ENTRY(_switch_to)
 
         /* Flush register file. */
 
-        call0   _spill_registers        # destroys a3, a4, and SAR
+        spill_registers_kernel
 
         /* Set kernel stack (and leave critical section)
          * Note: It's save to set it here. The stack will not be overwritten
@@ -1851,13 +1864,13 @@ ENTRY(_switch_to)
 
         /* restore context of the task 'next' */
 
-        l32i    a0, a13, THREAD_RA      # restore return address
-        l32i    a1, a13, THREAD_SP      # restore stack pointer
+        l32i    a0, a11, THREAD_RA      # restore return address
+        l32i    a1, a11, THREAD_SP      # restore stack pointer
 
-        load_xtregs_user a5 a6 a8 a9 a10 a11 THREAD_XTREGS_USER
+        load_xtregs_user a5 a6 a8 a9 a12 a13 THREAD_XTREGS_USER
 
         wsr     a14, ps
-        mov     a2, a12                 # return 'prev'
+        mov     a2, a10                 # return 'prev'
         rsync
 
         retw
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index 482868a2de6e..3eee94f621eb 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -155,18 +155,6 @@ void __init init_IRQ(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void route_irq(struct irq_data *data, unsigned int irq, unsigned int cpu)
-{
-        struct irq_desc *desc = irq_to_desc(irq);
-        struct irq_chip *chip = irq_data_get_irq_chip(data);
-        unsigned long flags;
-
-        raw_spin_lock_irqsave(&desc->lock, flags);
-        if (chip->irq_set_affinity)
-                chip->irq_set_affinity(data, cpumask_of(cpu), false);
-        raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
 /*
  * The CPU has been marked offline.  Migrate IRQs off this CPU.  If
  * the affinity settings do not allow other CPUs, force them onto any
@@ -175,10 +163,9 @@ static void route_irq(struct irq_data *data, unsigned int irq, unsigned int cpu)
 void migrate_irqs(void)
 {
         unsigned int i, cpu = smp_processor_id();
-        struct irq_desc *desc;
 
-        for_each_irq_desc(i, desc) {
-                struct irq_data *data = irq_desc_get_irq_data(desc);
+        for_each_active_irq(i) {
+                struct irq_data *data = irq_get_irq_data(i);
                 unsigned int newcpu;
 
                 if (irqd_is_per_cpu(data))
@@ -194,11 +181,8 @@ void migrate_irqs(void)
                                             i, cpu);
 
                         cpumask_setall(data->affinity);
-                        newcpu = cpumask_any_and(data->affinity,
-                                                 cpu_online_mask);
                 }
-
-                route_irq(data, i, newcpu);
+                irq_set_affinity(i, data->affinity);
         }
 }
 #endif /* CONFIG_HOTPLUG_CPU */
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 7d12af1317f1..84fe931bb60e 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -22,6 +22,7 @@
 #include <linux/bootmem.h>
 #include <linux/kernel.h>
 #include <linux/percpu.h>
+#include <linux/clk-provider.h>
 #include <linux/cpu.h>
 #include <linux/of_fdt.h>
 #include <linux/of_platform.h>
@@ -276,6 +277,7 @@ void __init early_init_devtree(void *params)
 
 static int __init xtensa_device_probe(void)
 {
+        of_clk_init(NULL);
         of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
         return 0;
 }
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 08b769d3b3a1..2a1823de69cc 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -30,6 +30,7 @@
 #include <asm/platform.h>
 
 unsigned long ccount_freq;              /* ccount Hz */
+EXPORT_SYMBOL(ccount_freq);
 
 static cycle_t ccount_read(struct clocksource *cs)
 {
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index cb8fd44caabc..f9e1ec346e35 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -235,7 +235,7 @@ ENTRY(_DoubleExceptionVector)
 
         /* Check for overflow/underflow exception, jump if overflow. */
 
-        _bbci.l a0, 6, _DoubleExceptionVector_WindowOverflow
+        bbci.l  a0, 6, _DoubleExceptionVector_WindowOverflow
 
         /*
          * Restart window underflow exception.
diff --git a/arch/xtensa/kernel/xtensa_ksyms.c b/arch/xtensa/kernel/xtensa_ksyms.c
index 74a60c7e085e..80b33ed51f31 100644
--- a/arch/xtensa/kernel/xtensa_ksyms.c
+++ b/arch/xtensa/kernel/xtensa_ksyms.c
@@ -122,9 +122,7 @@ EXPORT_SYMBOL(insw);
 EXPORT_SYMBOL(insl);
 
 extern long common_exception_return;
-extern long _spill_registers;
 EXPORT_SYMBOL(common_exception_return);
-EXPORT_SYMBOL(_spill_registers);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(_mcount);
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 479d7537a32a..aff108df92d3 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -90,7 +90,7 @@ int __init mem_reserve(unsigned long start, unsigned long end, int must_exist)
 
 
 /*
- * Initialize the bootmem system and give it all the memory we have available.
+ * Initialize the bootmem system and give it all low memory we have available.
  */
 
 void __init bootmem_init(void)
@@ -142,9 +142,14 @@ void __init bootmem_init(void)
 
         /* Add all remaining memory pieces into the bootmem map */
 
-        for (i=0; i<sysmem.nr_banks; i++)
-                free_bootmem(sysmem.bank[i].start,
-                             sysmem.bank[i].end - sysmem.bank[i].start);
+        for (i = 0; i < sysmem.nr_banks; i++) {
+                if (sysmem.bank[i].start >> PAGE_SHIFT < max_low_pfn) {
+                        unsigned long end = min(max_low_pfn << PAGE_SHIFT,
+                                                sysmem.bank[i].end);
+                        free_bootmem(sysmem.bank[i].start,
+                                     end - sysmem.bank[i].start);
+                }
+        }
 
 }
 
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
index 36ec171698b8..861203e958da 100644
--- a/arch/xtensa/mm/mmu.c
+++ b/arch/xtensa/mm/mmu.c
@@ -39,7 +39,7 @@ void init_mmu(void)
         set_itlbcfg_register(0);
         set_dtlbcfg_register(0);
 #endif
-#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && CONFIG_OF
+#if XCHAL_HAVE_PTP_MMU && XCHAL_HAVE_SPANNING_WAY && defined(CONFIG_OF)
         /*
          * Update the IO area mapping in case xtensa_kio_paddr has changed
          */
diff --git a/arch/xtensa/platforms/xtfpga/setup.c b/arch/xtensa/platforms/xtfpga/setup.c
index 800227862fe8..57fd08b36f51 100644
--- a/arch/xtensa/platforms/xtfpga/setup.c
+++ b/arch/xtensa/platforms/xtfpga/setup.c
@@ -135,11 +135,11 @@ static void __init update_local_mac(struct device_node *node)
 
 static int __init machine_setup(void)
 {
-        struct device_node *serial;
+        struct device_node *clock;
         struct device_node *eth = NULL;
 
-        for_each_compatible_node(serial, NULL, "ns16550a")
-                update_clock_frequency(serial);
+        for_each_node_by_name(clock, "main-oscillator")
+                update_clock_frequency(clock);
 
         if ((eth = of_find_compatible_node(eth, NULL, "opencores,ethoc")))
                 update_local_mac(eth);
@@ -290,6 +290,7 @@ static int __init xtavnet_init(void)
          * knows whether they set it correctly on the DIP switches.
          */
         pr_info("XTFPGA: Ethernet MAC %pM\n", ethoc_pdata.hwaddr);
+        ethoc_pdata.eth_clkfreq = *(long *)XTFPGA_CLKFRQ_VADDR;
 
         return 0;
 }
diff --git a/arch/xtensa/variants/fsf/include/variant/tie.h b/arch/xtensa/variants/fsf/include/variant/tie.h
index bf4020116df5..244cdea4dee5 100644
--- a/arch/xtensa/variants/fsf/include/variant/tie.h
+++ b/arch/xtensa/variants/fsf/include/variant/tie.h
@@ -18,13 +18,6 @@
 #define XCHAL_CP_MASK                   0x00    /* bitmask of all CPs by ID */
 #define XCHAL_CP_PORT_MASK              0x00    /* bitmask of only port CPs */
 
-/*  Basic parameters of each coprocessor:  */
-#define XCHAL_CP7_NAME                  "XTIOP"
-#define XCHAL_CP7_IDENT                 XTIOP
-#define XCHAL_CP7_SA_SIZE               0       /* size of state save area */
-#define XCHAL_CP7_SA_ALIGN              1       /* min alignment of save area */
-#define XCHAL_CP_ID_XTIOP               7       /* coprocessor ID (0..7) */
-
 /*  Filler info for unassigned coprocessors, to simplify arrays etc:  */
 #define XCHAL_NCP_SA_SIZE               0
 #define XCHAL_NCP_SA_ALIGN              1
@@ -42,6 +35,8 @@
 #define XCHAL_CP5_SA_ALIGN              1
 #define XCHAL_CP6_SA_SIZE               0
 #define XCHAL_CP6_SA_ALIGN              1
+#define XCHAL_CP7_SA_SIZE               0
+#define XCHAL_CP7_SA_ALIGN              1
 
 /*  Save area for non-coprocessor optional and custom (TIE) state:  */
 #define XCHAL_NCP_SA_SIZE               0